Skip to main content
Glama

Feedback on a review finding

godot_feedback

Report whether a Godotwright review finding was a false alarm or valid, or whether a lesson helped, so later local reviews adjust ranking based on verified code checks.

Instructions

Tell Godotwright that a godot_review finding was wrong (a false alarm you verified) or right, or whether a lesson from godot_lessons helped. Pass finding (the line as godot_review printed it) or lesson (its id), not both. A finding marked wrong is hidden in later reviews on this machine, and a rule marked wrong far more often than right is reported one level lower; a lesson marked right ranks higher, wrong lower. Only use it after checking the code (godot_api, godot_check); fix real findings instead. It writes only to the local learning file (godotwright learn reset forgets it). An error when the line is not a finding, the lesson does not exist, or learning is off.

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": {
      "verdict": "<verdict>"
    },
    "name": "godot_feedback"
  }
}

Input Schema

NameRequiredDescriptionDefault
lessonNoa lesson id from godot_lessons, e.g. physics/moving-platform-velocity
findingNothe finding line, e.g. res://player.gd:12: error [api/unknown-member] ...
verdictYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.2.2
    • addedInput schema / properties / lesson
      Added value: +{
      +  "description": "a lesson id from godot_lessons, e.g. physics/moving-platform-velocity",
      +  "type": "string"
      +}
    • changedInput schema / required
      Previous value: -[
      -  "finding",
      -  "verdict"
      -]New value: +[
      +  "verdict"
      +]
  2. First observedv0.1.0

TDQS

A4.8/5.0
Behavior5/5

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

The annotations only declare the generic profile (not read-only, not destructive, not idempotent, closed-world), while the description discloses the actual consequences: a wrong finding is hidden in later reviews on this machine, a rule wrong far more often than right is reported one level lower, and lesson rankings shift. It further scopes the write to the local learning file, gives the reset path (`godotwright learn reset`), and lists the three error conditions.

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 content is front-loaded: identity of the action first, then the argument rule, then effects, then preconditions and errors. Every sentence carries information, but several are densely packed clauses joined by semicolons, which slightly costs readability.

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 3-parameter mutation with no output schema, the description covers everything an agent needs: what triggers it, what persists, how to undo, how outcomes affect future reviews, and what errors mean. Nothing material about calling it correctly is missing.

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 67%, and the description adds the key constraint the schema cannot express: pass `finding` or `lesson`, never both, with `finding` being the line exactly as godot_review printed it and `lesson` being its id. It also explains what 'wrong' and 'right' mean for each target type. The verdict enum values themselves are only implicitly defined, keeping this below a 5.

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 names a specific verb (tell/report a verdict) and specific resources (a godot_review finding line or a godot_lessons lesson id), and it names the siblings that produce those inputs. An agent can distinguish this from godot_review and godot_lessons without opening any schema.

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 gives an explicit precondition ('Only use it after checking the code (godot_api, godot_check)') and an explicit exclusion ('fix real findings instead'), naming the alternative tools to use first. It also states the mutual exclusivity rule between finding and lesson, so there is nothing left to infer about when this applies.

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