Mushi-Mushi

Run Sonnet-as-Judge

trigger_judge

Idempotent

Queue automated grading of recent fix quality across projects before shipping. Dispatches one judge-batch job per project and returns the count; scores land asynchronously in judge_results.

Instructions

Queue the Sonnet-as-Judge to grade recent fix quality across accessible projects. Returns { dispatched: number } — one judge-batch job per project; scores land asynchronously in judge_results (read back with run_nl_query). Write; consumes LLM budget. Idempotent within a short window. Use before shipping to vet fix quality; use get_fix_timeline to inspect a single attempt instead.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`limit`	No	Max reports to judge in this batch (default 25, max 100)
`projectId`	No	Restrict to one project when the API key owns multiple (`project_id` is accepted too.)

Output Schema

TableJSON Schema

Name	Required	Description	Default
`dispatched`	Yes	Number of judge-batch jobs dispatched (one per accessible project)

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedv0.1.12Sep 24, 2026

changedInput schema / properties / projectId / description

Previous value: -"Restrict to one project when the API key owns multiple"New value: +"Restrict to one project when the API key owns multiple (`project_id` is accepted too.)"

Changed2 schema fields changedv0.1.10Sep 15, 2026

changedInput schema / $schema

Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"

changedOutput schema / $schema

Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"

Changed1 schema field changedv0.1.2Jun 28, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "additionalProperties": false,
+  "properties": {
+    "dispatched": {
+      "description": "Number of judge-batch jobs dispatched (one per accessible project)",
+      "type": "number"
+    }
+  },
+  "required": [
+    "dispatched"
+  ],
+  "type": "object"
+}

First observedv0.1.0Jun 24, 2026

TDQS

A4.3/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=false, destructiveHint=false, and idempotentHint=true. The description adds valuable context: it's a write operation that consumes LLM budget, idempotent only 'within a short window', and results land asynchronously in judge_results. This goes beyond the annotations by clarifying the asynchronous nature and budget consumption, though it does not detail failure modes.

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?

The description is well-structured, front-loading the core action and then layering return type, side effects, idempotency, and usage guidance. It is dense but every sentence earns its place, though it could be slightly tightened without losing meaning.

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?

An output schema exists, so return values are covered. The description includes how to read results (via run_nl_query), mentions the asynchronous nature, and gives usage context. It lacks error handling or prerequisite details, but given the annotations and simplicity of the tool, it is reasonably complete.

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 description coverage is 100%, and both parameters have meaningful descriptions ('Max reports to judge', 'Restrict to one project'). The tool description adds no additional parameter guidance beyond what the schema provides, so the baseline of 3 is appropriate.

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 the verb 'Queue', the resource 'Sonnet-as-Judge', and the purpose 'to grade recent fix quality across accessible projects'. It also differentiates from the sibling get_fix_timeline by naming it as an alternative for single-attempt inspection. This is specific and unambiguous.

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?

The description explicitly tells when to use it ('Use before shipping to vet fix quality') and when not to ('use get_fix_timeline to inspect a single attempt instead'). This provides clear decision rules without requiring the agent to infer context.

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