Skip to main content
Glama

Take My Repo

Search projects, models and demos

search
Read-only

Search GitHub repositories and Hugging Face models, demos and datasets together, by what the person wants to do. Returns ranked results with license, popularity, last update, where each value was read, and whether the maintainer declared support for the given operating system. 'fit' is 'declared' or 'unknown'; it is never a guess.

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": {
      "query": "<query>"
    },
    "name": "search"
  }
}

Input Schema

NameRequiredDescriptionDefault
osNoThe person's operating system, to put declared matches first.
kindNoLimit to one type. Default: all.
queryYesWhat the person wants to build or run, in plain words. A few keywords work best.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already cover read-only and open-world behavior, and the description adds genuinely new behavioral context: ranked results carrying license, popularity, last update, per-field provenance ('where each value was read'), and OS support, plus the explicit honesty guarantee that 'fit' is only 'declared' or 'unknown' and never a guess. That provenance and non-guessing disclosure is exactly the kind of thing an agent cannot infer from annotations. Missing only result-count/pagination behavior.

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 action, then return contents, then the fit caveat, in three purposeful sentences. The fit sentence is slightly dense but earns its place; nothing is padded or restated from the title.

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?

For a simple read-only three-parameter search with no output schema, the description does the needed work by enumerating the returned fields, their provenance, and the semantics of 'fit'. Gaps remain around result volume, ranking mechanics, and whether the search paginates, which matters for an open-world search tool.

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% with clear enum definitions for os and kind, so the baseline applies. The description adds little param-specific detail beyond reinforcing that queries are intent-based ('by what the person wants to do') and that OS influences ordering via declared matches, but does not explain how kind and os interact or what happens when os is omitted.

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?

States a concrete verb ('Search') plus the exact corpora searched (GitHub repositories and Hugging Face models, demos, datasets) and the framing ('by what the person wants to do'). That scope is specific enough that an agent can tell it apart from find_people, get_resource, get_reviews, or get_install_plan without opening any schema.

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?

Conveys usage context through 'by what the person wants to do' and the 'together' framing, which implies this is the broad discovery entry point, and the schema says kind defaults to all. But it never states when to prefer this over a sibling like get_resource or get_install_plan, nor any exclusions or follow-up path after searching.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources