Skip to main content
Glama
io.github.sionjang101-create/taskattest

io.github.sionjang101-create/taskattest

Replay an evidence bundle

replay_evidence
Read-onlyIdempotent

Re-runs the verification recorded in an evidence manifest and reports whether the digest still matches, so you can test if a claimed verdict holds up instead of trusting it.

Instructions

Re-run the verification recorded in an evidence manifest and report whether the digest still matches. Use this to test whether a claimed verdict holds up, rather than taking the manifest's word for it.

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": {
      "manifest_path": "<manifest_path>"
    },
    "name": "replay_evidence"
  }
}

Input Schema

NameRequiredDescriptionDefault
manifest_pathYesPath to a manifest.json from a previous run.

Output Schema

NameRequiredDescriptionDefault
checksNo
spec_pathNo
digest_matchYes
verdict_matchYes
recorded_digestYes
recorded_verdictYes
recomputed_digestYes
recomputed_verdictYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive, and closed-world, so safety is covered. The description adds genuinely new behavior: this actually re-executes the recorded verification rather than reporting stored results, and it reports digest-match outcome. It still omits what happens when the manifest is stale or the replay fails, but the key behavioral distinction from a plain read is disclosed.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, both earning their place: the first states the action and result, the second states the motivation and when to prefer it. Nothing is padded or repeated.

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?

For a one-parameter, read-only, closed-world tool with full schema coverage and an output schema that carries the return values, this is sufficient. Safety is covered by annotations, parameters by the schema, and purpose plus motivation by the description.

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?

There is a single parameter at 100% schema coverage, where the schema already explains it as a 'Path to a manifest.json from a previous run.' The description adds no path format, relative-vs-absolute, or validity guidance beyond that. Baseline 3 applies since the schema does the work.

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?

Uses a specific verb+resource combination: 'Re-run the verification recorded in an evidence manifest and report whether the digest still matches.' The purpose and the returned result are unambiguous. It does not differentiate itself from the sibling verify_task, which an agent could plausibly confuse with this replay operation, so it falls short of 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 Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives a clear usage purpose: 'Use this to test whether a claimed verdict holds up, rather than taking the manifest's word for it.' This clearly frames when the tool is appropriate (distrust of a claimed verdict). It provides no explicit exclusions or named alternatives, so no 5.

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