Skip to main content
Glama

Search APIs and models

search_apis
Read-onlyIdempotent

Find OpenAny models and APIs by keywords and optional kind (api, model, or all; default all), provider, category, data_platform, data_product or capability. Model hits include model_id and, when the model catalog provides them, modalities, context length and a pricing summary. Returns bounded summaries and required inputs, not full schemas. Then call get_api. Keyword search supports limited bilingual aliases; it is not general semantic search.

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_apis"
  }
}

Input Schema

NameRequiredDescriptionDefault
kindNo
limitNo
queryNo
cursorNo
categoryNo
providerNo
capabilityNo
data_productNo
data_platformNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive, closed-world behavior, so the bar is lower, yet the description adds real value: it discloses that results are bounded summaries with required inputs rather than full schemas, enumerates the extra model-hit fields (model_id, modalities, context length, pricing summary), and warns about alias-limited matching. It stops short of describing pagination or merge behavior across kind values.

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?

The definition is front-loaded with purpose before payoff details, and each sentence contributes something (scope, return shape, follow-up call, search limitation). It is slightly dense and clause-heavy in the first sentence, but there is no filler.

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 nine parameters, no output schema, and no descriptions in the schema, the description does well: it characterizes the return payload and the recommended next step. The omission of limit/cursor semantics leaves an agent guessing about page size and continuation, which is the main completeness shortfall.

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 description coverage is 0%, so the description carries the full burden and largely meets it: it explains kind's allowed values and default, and names provider, category, data_platform, data_product, capability, and the keyword query. Only limit and cursor are left unexplained, which is a real gap but a small fraction of nine parameters.

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?

The description opens with a specific verb and resource ('Find OpenAny models and APIs') and immediately scopes the search dimensions (keywords, kind, provider, category, data_platform, data_product, capability). It further distinguishes itself from get_api by stating it returns 'bounded summaries and required inputs, not full schemas,' so an agent knows this is a discovery tool rather than a detail fetch.

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

Usage Guidelines4/5

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

Explicit routing is given: 'Then call get_api' establishes the follow-up path after a hit. The caveat that keyword search 'supports limited bilingual aliases; it is not general semantic search' sets a clear expectation about query behavior. It does not explicitly state when to prefer openany_overview or run_api, but the discovery-versus-detail split is clear enough to place the tool.

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.