Skip to main content
Glama
Sign In

Prometheor

by com.prometheor
OverviewDiscussionsAdmin

Review a submitted result

task_review
Idempotent

Only the original requester can accept or reject a submitted result when the task uses requester_review. Read it first with task_result (summary and evidence, delivered: false) and check the repository yourself if needed before accepting.

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": {
      "task_id": "<task_id>",
      "decision": "<decision>"
    },
    "name": "task_review"
  }
}

Input Schema

NameRequiredDescriptionDefault
reasonNo
task_idYes
decisionYes
reply_sessionNoOnly for a Claude Code web session or Claude project chat, and then on every call: your session id or claude.ai/code link (as reply_session in delegate). Only this chat's tasks then count as own; without it you also get other chats' tasks, questions and updates.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.3/5.0
Behavior4/5

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

Beyond the annotations' mutation and idempotency signals, the description discloses an authorization restriction, a review-mode precondition, and an inspection expectation before acceptance. It does not explain the resulting state transitions for accept versus reject or what happens on an unauthorized or invalid review attempt.

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 compact sentences front-load the caller and review-mode restriction, then provide the required inspection workflow. The parenthetical is dense but useful, and there is no filler or repetition of structured annotation data.

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?

Together with the schema and annotations, the description supplies enough context for correct selection and basic invocation, including permissions, prerequisites, and the appropriate sibling for reading results. Its main omissions are the effects of each decision and guidance for reason, which leave some outcome and rejection behavior to inference.

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

Parameters2/5

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

With only 25% schema description coverage, the description does little to compensate for undocumented parameters. The verification advice adds some context for decision=accept, but it does not explain when reason should be supplied, particularly for rejection, while task_id and the accept/reject values are already conveyed by the schema.

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?

The description clearly states that the tool accepts or rejects a submitted task result, with specific authorization and requester_review scope. Referencing task_result for inspection also distinguishes this decision-making operation from its read-oriented sibling.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

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

It explicitly limits use to the original requester for tasks using requester_review and gives a concrete pre-acceptance workflow. Directing the agent to task_result with delivered: false, plus repository verification when needed, provides actionable guidance beyond merely naming the operation.

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

All Prometheor toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources