Search Tools

post/v1/tools/search

Search tools using semantic search.

Requires tool embedding to be enabled (embed_tools=True). Uses vector search, full-text search, or hybrid mode to find tools matching the query.

Returns tools ranked by relevance with their search scores.

Body ParametersExpand Collapse

limit: optional number

Maximum number of results to return.

maximum100

minimum1

query: optional string

Text query for semantic search.

search_mode: optional "vector" or "fts" or "hybrid"

Search mode: vector, fts, or hybrid.

Accepts one of the following:

"vector"

"fts"

"hybrid"

tags: optional array of string

Filter by tags (match any).

tool_types: optional array of string

Filter by tool types (e.g., 'custom', 'letta_core').

ReturnsExpand Collapse

combined_score: number

Combined relevance score (RRF for hybrid mode).

tool: Tool { id, args_json_schema, created_by_id, 14 more }

The matched tool.

id: string

The human-friendly ID of the Tool

args_json_schema: optional map[unknown]

The args JSON schema of the function.

created_by_id: optional string

The id of the user that made this Tool.

default_requires_approval: optional boolean

Default value for whether or not executing this tool requires approval.

description: optional string

The description of the tool.

enable_parallel_execution: optional boolean

If set to True, then this tool will potentially be executed concurrently with other tools. Default False.

json_schema: optional map[unknown]

The JSON schema of the function.

last_updated_by_id: optional string

The id of the user that made this Tool.

metadata_: optional map[unknown]

A dictionary of additional metadata for the tool.

The name of the function.

npm_requirements: optional array of NpmRequirement { name, version }

Optional list of npm packages required by this tool.

Name of the npm package.

minLength1

version: optional string

Optional version of the package, following semantic versioning.

pip_requirements: optional array of PipRequirement { name, version }

Optional list of pip packages required by this tool.

Name of the pip package.

minLength1

version: optional string

Optional version of the package, following semantic versioning.

return_char_limit: optional number

The maximum number of characters in the response.

maximum1000000

minimum1

source_code: optional string

The source code of the function.

source_type: optional string

The type of the source code.

tags: optional array of string

Metadata tags.

tool_type: optional ToolType

The type of the tool.

Accepts one of the following:

"custom"

"letta_core"

"letta_memory_core"

"letta_multi_agent_core"

"letta_sleeptime_core"

"letta_voice_sleeptime_core"

"letta_builtin"

"letta_files_core"

"external_langchain"

"external_composio"

"external_mcp"

embedded_text: optional string

The embedded text content used for matching.

fts_rank: optional number

Full-text search rank position.

vector_rank: optional number

Vector search rank position.

Search Tools

curl https://api.letta.com/v1/tools/search \
    -H 'Content-Type: application/json' \
    -H "Authorization: Bearer $LETTA_API_KEY" \
    -d '{}'

[
  {
    "combined_score": 0,
    "tool": {
      "id": "tool-123e4567-e89b-12d3-a456-426614174000",
      "args_json_schema": {
        "foo": "bar"
      },
      "created_by_id": "created_by_id",
      "default_requires_approval": true,
      "description": "description",
      "enable_parallel_execution": true,
      "json_schema": {
        "foo": "bar"
      },
      "last_updated_by_id": "last_updated_by_id",
      "metadata_": {
        "foo": "bar"
      },
      "name": "name",
      "npm_requirements": [
        {
          "name": "x",
          "version": "version"
        }
      ],
      "pip_requirements": [
        {
          "name": "x",
          "version": "version"
        }
      ],
      "return_char_limit": 1,
      "source_code": "source_code",
      "source_type": "source_type",
      "tags": [
        "string"
      ],
      "tool_type": "custom"
    },
    "embedded_text": "embedded_text",
    "fts_rank": 0,
    "vector_rank": 0
  }
]

Returns Examples

[
  {
    "combined_score": 0,
    "tool": {
      "id": "tool-123e4567-e89b-12d3-a456-426614174000",
      "args_json_schema": {
        "foo": "bar"
      },
      "created_by_id": "created_by_id",
      "default_requires_approval": true,
      "description": "description",
      "enable_parallel_execution": true,
      "json_schema": {
        "foo": "bar"
      },
      "last_updated_by_id": "last_updated_by_id",
      "metadata_": {
        "foo": "bar"
      },
      "name": "name",
      "npm_requirements": [
        {
          "name": "x",
          "version": "version"
        }
      ],
      "pip_requirements": [
        {
          "name": "x",
          "version": "version"
        }
      ],
      "return_char_limit": 1,
      "source_code": "source_code",
      "source_type": "source_type",
      "tags": [
        "string"
      ],
      "tool_type": "custom"
    },
    "embedded_text": "embedded_text",
    "fts_rank": 0,
    "vector_rank": 0
  }
]