Skip to main content
Glama

EasyCanDo

Search tools

search_tools
Read-onlyIdempotent

Find tools in the EasyCanDo catalog for one step of a build. Give a short query saying what the step does, and have and want when you know what goes in and what should come out. Returns up to 10 previews, best first: slug, one-line summary, the capability that matched with its input and output types, API status, price tier, the date it was checked and page URL, plus the arguments for the next page. Call get_tool before writing integration code.

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
freeNoOnly tools that are free or have a free tier.
haveNoWhat the step starts with. One of: words (words: text, query, message, social-post); photos (photos and images: image, image-mask, 3d); video (video: video); sound (voice and sound: audio-speech, audio, audio-music, audio-sfx); documents (documents: document); links (web links: url, webpage); places (places: geo); data (numbers and data: structured, timeseries, event-stream, embedding); code (code: code); money (money: money); people (people: profile); dates (dates and events: schedule). A type id in parentheses also works, and stands for the id before it.
liveNoOnly tools with live or real-time data.
wantNoWhat the step should produce. One of: words (words: text, query, message, social-post); photos (photos and images: image, image-mask, 3d); video (video: video); sound (voice and sound: audio-speech, audio, audio-music, audio-sfx); documents (documents: document); links (web links: url, webpage); places (places: geo); data (numbers and data: structured, timeseries, event-stream, embedding); code (code: code); money (money: money); people (people: profile); dates (dates and events: schedule); done (something done: action:publish, action:message, action:money, action:world, action:software, action:browser, action:schedule, action:record, physical-item). A type id in parentheses also works, and stands for the id before it. “done” means the tool acts: it posts, sends, pays, books or changes something.
groupNoOnly one group. One of: images (make, edit and fix pictures); video (make and edit video, avatars and 3d); voice (speak, transcribe, compose and clean up sound); design (make documents, slides and designs); ai (language models and agents that think and act); reading (read text out of pages, photos, audio and video); web (search the web and follow the news); social (read what people post and say); knowledge (papers, books, records and public data); world (weather, sky, earth, flights and places); posting (publish posts and send messages); money (markets, payments, stores and ads); home (lights, devices, deliveries and real things); mac (tools that run on your own mac, so nothing leaves it); building (code, data, hosting and the parts apps are made of).
limitNoResults per page, 1 to 10. Default 5.
localNoOnly tools that run on the user’s own machine.
queryNoWhat the step does, in a few words: “transcribe audio”, “vector database”, “send sms”.
offsetNoResults to skip. Use the next-page arguments a search returns.
officialNoOnly tools with an official API.

Output Schema

NameRequiredDescriptionDefault
nextYesThe arguments for the next page, to send as they are. Null on the last page.
noteYes
totalYesResults in all, across every page, looser matches left out. With fallback true, the tools the filters leave.
looserYesLooser matches left out: they match only part of the query, or only a side feature.
offsetYes
resultsYes
widenedYesResults after the ones that pass have and want: matches for the query with other inputs or outputs. search_tools adds them only when fewer than 3 tools pass. The note says how many passed.
fallbackYesTrue when nothing matched the query. With have or want, results are every tool those filters leave, best known first, ties by name; without, results are empty. The note says how to search instead.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Annotations already declare this a read-only, idempotent, non-destructive, closed-world read, so the description does not need to restate safety. Instead it adds behavior annotations do not carry: up to 10 previews per call, best-first ordering, the exact preview fields (slug, summary, matched capability with input/output types, API status, price tier, checked date, page URL), and that next-page arguments are returned for paging.

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?

Four sentences, front-loaded with purpose, then arguments, then return shape, then the follow-up rule; nothing is repeated from the schema verbatim. It is dense — the return-value sentence is a long field list — but each sentence carries distinct information.

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 10 optional parameters, all-optional requirements, full schema coverage, and an output schema, the description supplies exactly the missing connective tissue: what a preview contains, how paging works, and the get_tool handoff. Nothing needed to invoke this correctly is absent.

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 schema baseline is 3; the description goes beyond it by explaining the intent behind query ("what the step does, in a few words") and the conditional use of have/want as input/output type filters. It does not cover the narrowing booleans (free, live, local, official, group) or limit/offset, which are adequately described in the schema.

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?

"Find tools in the EasyCanDo catalog for one step of a build" names a specific verb (find/search) and resource (tool catalog), and scopes it to a single build step, which separates it from get_tool (details) and find_chains (multi-step). An agent can tell what this returns and when it applies without opening the schema.

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 states the operating context (one step of a build), how to phrase the query, when to supply have/want ("when you know what goes in and what should come out"), and explicitly routes follow-up work to get_tool before writing integration code. That is an explicit use-and-handoff rule rather than implied usage.

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