Skip to main content
Glama
io.github.datumline/agent-guard

io.github.datumline/agent-guard

Official
by datumline

Verify an agent's completion claim

verify_completion_claim
Read-only

Verify an AI agent's completion claim by checking claimed files, JSON, URLs, and hashes; returns a receipt verdict to catch missing or failing artifacts before accepting work.

Instructions

Check an AI agent's claim that a job is done against the artifacts it says it produced. Returns a JSON receipt whose 'verdict' is VERIFIED (every artifact present and passing), FAILED (an artifact fails a check), FALSE_DONE (the job is claimed COMPLETED/DONE but an artifact is missing) or UNVERIFIABLE (the manifest names no artifacts). Treat anything other than VERIFIED as not done. Artifact types: file (path, min_bytes, min_lines, must_contain, sha256), json (path, required_keys), url (url, status, must_contain). Relative paths resolve against the server's working directory.

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": "verify_completion_claim"
  }
}

Input Schema

NameRequiredDescriptionDefault
manifestNoManifest: {job, claimed_status, artifacts:[{type, path|url, ...checks}]}
manifest_pathNoPath to a manifest JSON file, instead of passing 'manifest'.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

A4.3/5.0
Behavior4/5

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

Annotations declare readOnlyHint=true and openWorldHint=true; the description adds substantial context beyond that: the full verdict taxonomy with the precise condition that triggers each, and the important quirk that relative paths resolve against the server's working directory. It does not cover error behavior or what happens if both manifest inputs are supplied, which keeps it from a 5.

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?

Front-loaded with purpose, then result semantics, then artifact taxonomy, then the path-resolution caveat — a sensible ordering with no filler. The prose is dense and the artifact-type list is packed into flowing sentences rather than line-broken, which slightly hurts scanability but wastes nothing.

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?

No output schema exists, and the description compensates by defining the receipt's verdict field and its possible values. With a nested manifest object and only two top-level params, the remaining gaps are the precedence between manifest and manifest_path and failure modes for unreadable manifests — minor for a read-only checker.

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 would be 3, but the description goes further by spelling out the nested manifest artifact vocabulary — file (path, min_bytes, min_lines, must_contain, sha256), json (path, required_keys), url (url, status, must_contain) — which the schema leaves as an opaque object. That is real meaning added beyond structured fields.

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: checking an agent's completion claim against the artifacts it claims to have produced. The opening sentence alone lets an agent know exactly what the tool does, and the verdict vocabulary reinforces the verification framing.

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 clear operational guidance on interpreting results — 'Treat anything other than VERIFIED as not done' — which tells the caller how to act on each outcome. It does not name exclusions or alternative tools, but no siblings exist and the intended context is unambiguous.

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

Deploy Server

Other Tools