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

io.github.sionjang101-create/taskattest

Verify a finished task

verify_task
Read-onlyIdempotent

Checks a task's produced files against a JSON definition-of-done spec, then returns pass, partial, or fail with a replayable evidence bundle for deterministic completion review.

Instructions

Judge whether a task is finished by checking the files it produced against a spec file that states the definition of done. Returns pass, partial or fail, plus a replayable evidence bundle. Deterministic: no model is consulted.

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": {
      "spec_path": "<spec_path>"
    },
    "name": "verify_task"
  }
}

Input Schema

NameRequiredDescriptionDefault
spec_pathYesPath to the task definition JSON.
evidence_dirNoWhere to write the evidence bundle. Defaults to <spec directory>/evidence.

Output Schema

NameRequiredDescriptionDefault
checksYes
task_idNo
verdictYes
warningsNo
judged_byYes
model_callsYes
evidence_dirYes
replay_commandNo
evidence_digestYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4/5.0
Behavior4/5

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

Annotations already cover read-only, idempotent, non-destructive and closed-world, so the bar is lower, but the description adds real signal: the result is deterministic with no model consulted, the verdict vocabulary is enumerated, and an evidence bundle is produced. It does not say what happens when the spec is missing or unreadable, nor how artifacts are discovered.

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, front-loaded with the core action, followed by return values and the determinism guarantee. Every clause carries information and nothing is repeated from the schema.

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?

With an output schema, rich annotations and full schema coverage, the description only needs to add judgment-level context, which it does. The remaining gap is failure/edge behavior — missing spec, unproducible evidence directory, or non-existent task files — which an agent would want before calling.

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 both parameters are already documented, including the evidence_dir default. The description contributes only the gloss that the spec file encodes the definition of done, which adds a little meaning to spec_path but nothing about formats or path resolution beyond the schema.

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?

States a specific verb and resource: it judges whether a task is finished by checking produced files against a spec file, and it names the three possible verdicts (pass, partial, fail). The scope is distinct enough that an agent can separate it from draft_spec or replay_evidence, though the description never names a sibling to route against explicitly.

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?

Usage context is clear: reach for it when a task's definition of done is captured in a spec file and you want a verdict on the produced artifacts. It gives no explicit exclusions or point-of-comparison to alternatives, which keeps it short of a full 5.

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