Skip to main content
Glama

Search software

search_software
Read-onlyIdempotent

Search the GitDex software directory by keyword and static filters. USE WHEN the user is looking for software, or before submitting software to check for an existing record. NEEDS a short keyword query (product type, key capability), optionally platforms and pricing. Matching is plain keyword matching, not semantic: send the distinctive nouns, and try a second phrasing before concluding nothing fits. Records are in English, Chinese or both, and both versions are searched: if the user's language finds nothing, try the keywords in the other one. NO side effects; public, no sign-in. An empty result only means nothing has been submitted to GitDex yet, never that such software does not exist. Searching never implies the user wants to publish a request.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "search_software"
  }
}

Input Schema

NameRequiredDescriptionDefault
sortNo'solved' puts first the software accepted by the most requesters (accepted_solution_count). That counts other people's needs, so still compare capabilities with this user's must-haves.relevance
limitNoPage size (max 50).
queryNoKeywords, e.g. 'offline notes markdown'.
offsetNoItems to skip; use next_offset from the previous page.
pricingNoMatch any of these pricing types.
categoryNoExact category tag.
platformsNoMatch software available on any of these platforms, e.g. ['ios','web','macos','windows','linux','android','cli'].
submitted_byNoOnly software submitted by this user: the `submitted_by.id` of a record. Lists one author's software.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.9/5.0
Behavior5/5

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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, so the description is not obligated to restate safety, yet it still adds substantive behavior: matching is plain keyword not semantic, retry with alternate phrasing, bilingual EN/ZH record coverage, public unauthenticated access, and the crucial semantics of an empty result. That empty-result caveat materially changes how an agent should report a miss to the user.

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?

Purpose and trigger come first, then requirements, then matching caveats, then result semantics. Every sentence carries non-redundant information; there is no throat-clearing or repetition of the schema.

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?

With 8 optional parameters and no output schema, the description covers the risk areas an agent actually needs: what to send, how matching works, cross-language retry, and how to interpret zero results. Pagination is the only thing implied rather than explained, and the offset description in the schema already references next_offset, so the gap is negligible.

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

Parameters4/5

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

Schema coverage is 100%, so the baseline is 3; the description earns one more by adding retrieval advice the schema does not carry, namely that the query should be short and composed of distinctive nouns rather than a sentence. It reinforces the major filters (platforms, pricing) but leaves sort, limit and offset entirely to the schema, which is acceptable given their inline descriptions.

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 opening sentence names a specific verb and resource ('Search the GitDex software directory') and immediately constrains scope to 'keyword and static filters', which is enough to distinguish it from sibling lookups like search_requests or get_software. The follow-up 'USE WHEN the user is looking for software' pins down the intent an agent must detect.

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?

It gives an explicit positive trigger (user looking for software), a second trigger (pre-submission duplicate check), and a negative guard ('Searching never implies the user wants to publish a request'), which prevents a costly misread of intent. Alternatives are not named by tool name, but the conditions that select this tool are fully spelled out.

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