Skip to main content
Glama
Sign In

Toolocate

by com.toolocate
OverviewDiscussionsAdmin

Search AI tools

search_tools
Read-onlyIdempotent

Search the Toolocate directory for AI tools that fit a task, optionally filtered by category, price, platform or agent access. Results come best name match first, then most notable, each with a one-line summary, pricing, platforms, agent access (API, MCP, CLI), the official url and pageUrl, the Toolocate page to cite. Leave query empty to browse a category or filter. For the full listing of one tool call get_tool.

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_tools"
  }
}

Input Schema

NameRequiredDescriptionDefault
agentNoOnly tools an agent can drive this way: mcp (an MCP server), api or cli.
limitNoTools per page (default 20).
priceNofree: any free option (fully_free, free_plan or open_source). paid: no free option. The other three pick one kind of free.
queryNoShort keywords, for example "video editor" or "transcribe meetings". Every word must appear in the tool's name, one-line summary, tags or category name, so prefer two or three distinctive words over a sentence.
cursorNonextCursor from the previous page, to get the next page.
localeNoLanguage of the text fields and of pageUrl (default en). A tool not yet written in that language comes back in English; its locale field says which language you got.
categoryNoA category slug or category group id from list_categories, for example "ai-image-generator" or "video".
platformNoOnly tools available on this platform.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already declare read-only, idempotent, closed-world behavior, and the description adds real value beyond them: result ordering ("best name match first, then most notable") and the full shape of each result item including pageUrl for citation. It does not cover result counts or rate/limit behavior beyond what the schema's limit/cursor already imply.

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?

Purpose and filters are front-loaded, then results, then the sibling escape hatch — a sensible order. The second sentence is long and packs many return fields, and the clause "the official url and pageUrl, the Toolocate page to cite" is slightly tangled, but nothing is truly wasted.

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 8 optional parameters and no output schema, the description correctly compensates by describing the returned fields and ranking, so an agent knows what comes back. The only gap is guidance on the other siblings (find_alternatives, list_categories) beyond the schema's incidental reference to list_categories.

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, but the description adds meaning the schema does not: the empty-query browse mode and the ranking rule that name matches dominate results. It also summarizes which filter dimensions exist (category, price, platform, agent access) without restating enum values.

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 specific verb and resource ("Search the Toolocate directory for AI tools") plus the filterable dimensions, and explicitly separates itself from get_tool ("For the full listing of one tool call get_tool"). An agent can distinguish this search tool from the detail-fetch sibling without opening either schema.

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?

Gives a clear usage context (find tools that fit a task) and an explicit fallback behavior: "Leave query empty to browse a category or filter." It routes the agent to get_tool for full detail. It does not mention when find_alternatives or list_categories would be preferable, so the alternative coverage is partial rather than complete.

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

All Toolocate toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources