Skip to main content
Glama

Best AI Things directory

Search AI tools

search_tools
Read-only

Finds AI tools in the Best AI Things directory for a job or by name, e.g. "remove background noise from podcasts" or "Cursor". Returns up to 10, best match first, each with its listing link.

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_tools"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoHow many to return (default 6).
queryYesWhat the tool should do, or its name.
pricingNoOnly tools with this pricing: free, freemium (free plan plus paid), paid, or contact (sales only).
categoryNoOnly this category (a slug from list_categories).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds real behavioral value beyond that: results are capped at 10, ordered best-match-first, and each carries a listing link — an agent can plan around the ranking and payload without guessing.

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?

A single front-loaded sentence covers purpose, both query modes, examples, and return shape with zero filler. The examples earn their place by showing the expected free-text granularity.

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 no output schema, the description supplies the essential return characteristics (count cap, ordering, listing link), and the params are fully covered by the schema. It stops short of describing empty-result behavior or fallback steps, which matters for a search entry point into a five-tool family.

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 query, limit, pricing, and category are all documented in structured data, which sets the baseline at 3. The description reinforces matching semantics ('for a job or by name') and the 10-result ceiling, but adds no detail on default limit, pricing semantics, or how category slugs are obtained.

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 — 'Finds AI tools in the Best AI Things directory' — and clarifies the two query modes (describe a job, or give a name) with concrete examples. Sibling differentiation is only implicit: the free-text search framing implies browse_category/list_categories are for category-driven exploration, but no sibling is named.

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 is implied by the examples ('remove background noise from podcasts', 'Cursor') rather than stated as when-to-use guidance. Nothing tells the agent when to prefer browse_category or find_alternatives over this search, or what to do when a query yields nothing.

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