Skip to main content
Glama

co.build

Search cobuild

search
Read-onlyIdempotent

Find devices and public-source mods by device name, model, feature, or project name. Use concise keywords, e.g. 'WHOOP', 'Kindle', or 'sleep export'. Returns descriptions and up to 20 matches per page. Pass nextOffset as offset with the same query and filters to continue. Use type: mod to skip devices, or deviceId/platform/kind/dataSource/needsSubscription/maxSetupMinutes to constrain mods. Filters require documented values and exclude unknowns; local dataSource is not an offline guarantee. Suggestions are approximate alternatives when no exact matches exist; confirm the intended device before setup. No match means no catalog evidence, not proof that a mod cannot exist.

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"
  }
}

Input Schema

NameRequiredDescriptionDefault
kindNo
typeNoall
limitNo
queryYesConcise keywords, not a sentence. Use filters for constraints.
offsetNo
deviceIdNoRestrict to this device, including explicitly linked cross-device mods.
platformNoRequire documented works or partly support; unknown support is excluded.
dataSourceNoCatalog data source, not a guarantee of offline operation.
maxSetupMinutesNo
needsSubscriptionNofalse requires an explicit no-subscription claim; unknown is excluded.

Output Schema

NameRequiredDescriptionDefault
totalYes
resultsYes
guidanceYes
truncatedYes
nextOffsetYes
suggestionsYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.5/5.0
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 operation, yet the description still adds substantial behavior: up to 20 matches per page, continuation via nextOffset with the same query and filters, and the rule that filters exclude unknown values rather than including them. It also flags two interpretive traps, that 'local' dataSource is not an offline guarantee and that no match is absence of catalog evidence rather than proof a mod cannot exist. This is exactly the kind of context structured fields cannot carry.

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 the query-shape rule are front-loaded, then pagination, then filters, then caveats, which is a sensible order. The prose is dense, with several long clauses packed into single sentences, so a reader must parse carefully, but no sentence is redundant filler.

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?

An output schema exists, so the description is not obliged to describe return values, and it correctly focuses instead on pagination mechanics and on how to read ambiguous results. For a 10-parameter search with enum filters and several interpretive traps, the definition supplies everything needed to call it and to reason about empty or approximate results.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With only 50% schema description coverage across 10 parameters, the description compensates well: it explains type as a device-skipping switch, names deviceId/platform/kind/dataSource/needsSubscription/maxSetupMinutes as mod constraints, clarifies that limit yields up to 20 per page, and describes offset as the value passed back from nextOffset. It further adds semantics the schema lacks, namely that filters require documented values and exclude unknowns, and that needsSubscription/dataSource answers are claims rather than guarantees.

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 two clearly scoped resources (devices and public-source mods) and enumerates the match keys: device name, model, feature, project name. That is far more than a restatement of the name 'search'. It stops short of distinguishing itself from catalog siblings such as get_mod, get_device, or get_top_mods, so an agent must infer that this is the exploratory entry point.

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?

It gives concrete usage guidance: concise keywords rather than sentences, with worked examples ('WHOOP', 'Kindle', 'sleep export'), and 'Use type: mod to skip devices' plus a list of filters for constraining mods. It also explains how to interpret edge results, telling the agent to confirm the intended device when only approximate suggestions appear. What is missing is routing to alternatives when a specific known entity is already identified.

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