Skip to main content
Glama

caps-describe_composition

Reports composition stamp data from cap-manifest.json—validation status, version, content digest, schema version, module count, and init order—so you can verify a build's trustworthiness and identity.

Instructions

Report the composition stamp from cap-manifest.json: whether the capability graph validated, the composition version, and the content binding digest, alongside the manifest schema version, the module count and initOrder. Answers 'is this build's composition trustworthy, and which build is it'. A project with no capabilities returns a present:false answer, not an error.

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": "caps-describe_composition"
  }
}

Input Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.9.0

TDQS

A4.3/5.0
Behavior4/5

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

With no annotations supplied, the description carries the full burden and does disclose a genuinely non-obvious behavior: a project with no capabilities returns a present:false answer instead of an error, which prevents an agent from misreading an empty result as failure. It also names the source of truth (cap-manifest.json), though it never explicitly labels the operation as read-only or describes the response shape beyond the field list.

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?

Three sentences, front-loaded with the resource and the returned fields, followed by the selection framing and the edge case. The middle clause is a dense six-item list but every item is a real return value, so nothing reads as padding.

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?

There is no output schema, so the description must convey what comes back, and it does so by naming each field plus the present:false case. Minor gaps remain: it does not say in what form the stamp is returned (structured object vs. text) or how the digest should be interpreted, but nothing needed to call it correctly is missing.

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?

The tool takes zero parameters, so there is no parameter meaning to add and the baseline applies. The description correctly implies a parameterless call by framing it as a pure report on the current manifest.

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 ('Report') and a precisely scoped resource ('the composition stamp from cap-manifest.json'), then enumerates the exact fields produced (validation result, composition version, content binding digest, schema version, module count, initOrder). That field-level enumeration makes it unmistakably distinct from caps-list_capabilities, which by name alone concerns listing capabilities rather than the manifest stamp.

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?

The framing question 'is this build's composition trustworthy, and which build is it' gives a clear selection context, and the empty-project clause tells the agent this tool is still the right call when no capabilities exist. It stops short of naming an alternative tool or stating when-not to use it, so it sits at clear-context rather than full routing guidance.

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