Skip to main content
Glama

search_docs

Retrieve architecture decisions, past bugs, best practices, and API contracts by semantically searching the entire project knowledge base. Use before writing code to avoid rework.

Instructions

Semantic search over the ENTIRE project knowledge base. Read-only, no side effects.

    Use this ALWAYS before writing or changing code to retrieve architecture
    decisions, past bugs, best practices, and API contracts.

    Prefer search_bugfixes() when debugging a specific error (searches only
    bugfix summaries). Use search_by_type() when you know the category.
    Use search_tests() when looking for test coverage.

    Args:
        query: What you want to know (natural language, be specific)
        top_k: Number of results (default: 5, increase for broad questions)
        project: Target project name (optional, defaults to active project)

    Returns:
        Ranked doc chunks, each showing source file:line, section heading,
        relevance %, doc type, and text. Returns a "no results" message with
        a rephrasing suggestion when nothing matches.
    

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
queryYes
top_kNo
projectNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes
Behavior5/5

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

With no annotations, the description fully discloses behavior: read-only, no side effects, and describes the return format including how 'no results' is handled with a rephrasing suggestion.

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

Conciseness5/5

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

Well-structured with clear sections: purpose, usage guidelines, args, returns. Every sentence is concise and contributes value, no redundancy.

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

Completeness5/5

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

Despite an output schema existing, the description covers all necessary context: purpose, usage rules, parameter semantics, and return details including edge cases. Complete for a search tool.

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

Parameters5/5

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

Schema has 0% description coverage, but the description explains each parameter: query as natural language, top_k with default and usage advice, and project as optional with default behavior, adding significant meaning.

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

Purpose5/5

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

The description clearly states 'Semantic search over the ENTIRE project knowledge base' with 'Read-only, no side effects', distinguishing it from sibling tools like search_bugfixes, search_by_type, and search_tests.

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

Usage Guidelines5/5

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

Explicitly advises 'Use this ALWAYS before writing or changing code' and provides clear alternatives: 'Prefer search_bugfixes() when debugging...', 'Use search_by_type() when you know the category.', 'Use search_tests() when looking for test coverage.'

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/dl4rce/flaiwheel'

If you have feedback or need assistance with the MCP directory API, please join our Discord server