Skip to main content
Glama

Find the AI infrastructure or tool action for a task

unfragile_find
Read-only

Finds the product, and the specific tool action, that does a task, across AI infrastructure (search APIs, models, inference, browsers, harnesses, compute) and the MCP servers, APIs, CLIs, SDKs and models in our index. Each result carries the label from our checks (verified and signed · official · checked: not enough evidence yet · found in code, not yet checked · demo or tutorial · failed its last check) and a signed receipt. answer: true adds a written, cited answer; false returns the ranked list. A fact we hold (a price, a limit, a model id) arrives in structuredContent.blocks (type 'fact') and at the start of the answer, never in results.

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": {
      "task": "<task>"
    },
    "name": "unfragile_find"
  }
}

Input Schema

NameRequiredDescriptionDefault
kindNoWith search: 'product' (which product does X), 'action' (the one operation to call) or 'model' (which AI model)
laneNofast: ranked results only · standard: results and a written, cited answer (default) · best: a freshly written answer
taskYesWhat you need done, in plain words
limitNoHow many results (default 5)
namedNoWith search: products the task names, so they lead
answerNoAlso return a written answer: the products that do it, each cited to its maker's own pages. Default here: true (this door has always answered); false lists the products without writing
intentNoDeprecated: the old name of `kind` (kept so 0.10 callers work)
searchNoOptional: your own 3-10 word search phrase; skips our reading step
max_ageNoSeconds: a remembered answer older than this is written afresh
session_idNoYour own id for this task (recorded on the receipt)
client_modelNoThe model that will read the answer (recorded on the receipt)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.7/5.0
Behavior4/5

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

Annotations are thin (readOnlyHint, openWorldHint), but the description adds real context: results carry trust labels from checks (verified and signed, official, checked, demo, failed last check) and a signed receipt, and facts are returned in structuredContent.blocks rather than results. It also discloses caching behavior via max_age and that session_id/client_model are recorded on the receipt. It still does not describe latency or ranking behavior beyond the lane names.

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 is front-loaded in the first clause, and the definition is dense but organized: what it finds, what results carry, then how answer/facts behave. The long parenthetical label list is bulky but each label is meaningful for interpreting results. A few clauses pack multiple ideas and could be split, costing the fifth point.

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?

For an 11-parameter, no-output-schema tool, the description covers the important unknowns: result labeling, the signed receipt, the answer-vs-list split, and where facts are surfaced. An agent can call it and interpret the shape of a response. Minor gaps remain around ranking and error behavior, but nothing critical is omitted.

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 coverage is 100%, so the schema already documents all 11 parameters, including enum values for kind, lane and intent. The description adds a little interpretation, notably that answer defaults to true at this door and that facts appear at the start of the answer. Beyond that it largely restates what the schema provides, which is the baseline 3 profile.

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 gives a specific verb and resource: it finds the product and the specific tool action for a task, across named categories (search APIs, models, inference, browsers, harnesses, compute) plus an index of MCP servers, APIs, CLIs, SDKs and models. That is concrete enough for an agent to know what comes back. It stops short of naming how it differs from unfragile_resolve or unfragile_verify, so it does not fully earn a 5.

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 through parameter semantics: lane fast/standard/best, answer true/false, kind product/action/model, and search 'skips our reading step'. These tell an agent how to tune a call but not when this tool is the right choice versus a sibling. There is no explicit when-not or alternative routing, leaving the agent to infer the boundary.

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.