Skip to main content
Glama
Sign In
cowork-semantic-search

cowork-semantic-search

by ZhuBit
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

index_folder

Idempotent

Index or re-index documents in a folder for semantic search, processing only changed files and storing embeddings in a local vector database.

Instructions

Index or re-index all documents in a folder for semantic search.

Scans the folder for supported document types (.txt, .md, .pdf, .docx, .pptx, .csv), extracts text, splits into chunks, computes embeddings, and stores them in a local vector database. Only processes files that have changed since the last indexing run. Safe to call multiple times — unchanged files are skipped automatically.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "folder_path": "<folder_path>"
    },
    "name": "index_folder"
  }
}

Input Schema

NameRequiredDescriptionDefault
recursiveNoWhether to index subdirectories recursively
file_typesNoFile extensions to index, e.g. ['.pdf', '.md']. Defaults to all supported types: .txt, .md, .pdf, .docx, .pptx, .csv
folder_pathYesAbsolute path to the folder to index

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.7/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare idempotentHint=true and destructiveHint=false, yet the description still adds real value: it enumerates the pipeline (scan, extract, chunk, embed, store in a local vector database), lists supported extensions, and explains the incremental 'changed since last run' behavior that justifies idempotency. It does not cover cost/duration, permission needs, or what happens on unsupported or missing paths.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the core purpose, then the mechanics, then the safety note — a sensible order. Minor redundancy: 'Only processes files that have changed since the last indexing run' and 'unchanged files are skipped automatically' say the same thing twice.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With an output schema present, return values need no explanation, and the description covers the operation pipeline, file-type scope, and idempotency well. What is missing is prerequisite/edge-case handling (nonexistent folder, unsupported files) and routing guidance against the three siblings.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline is 3. The description restates the supported file-type list already in the file_types schema description and says nothing extra about recursive or folder_path, adding essentially no semantics beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource — indexing/re-indexing all documents in a folder for semantic search — and the scope ('all documents in a folder') implicitly separates it from the single-file sibling reindex_file. It never names or explicitly contrasts with get_index_status or semantic_search, so differentiation is left partly to inference.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage context is implied by 'Only processes files that have changed' and 'Safe to call multiple times,' which tell an agent this is a repeatable maintenance operation. However, there is no explicit when-to-use guidance or routing to alternatives (e.g., reindex_file for a single document, or get_index_status to check before indexing).

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools