What is wrong, and in which order to fix it

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

Annotations cover the safety profile (read-only, idempotent, non-destructive), and the description adds substantially beyond that: Godot execution is conditional on installation, duplicate findings are collapsed by cause ('twenty findings from one missing file are one problem'), output is severity-ordered with Godot errors before review errors, and it ends with numbered next steps. The only redundancy is the phrase 'Read-only', which merely restates readOnlyHint.

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

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

Front-loaded with the decision cue before any mechanics, and every clause carries information (grouping, ordering, per-finding payload, automation handoff). It is a long run-on sentence with nested parentheticals that slightly slows parsing, but no sentence is filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description carries the burden of explaining returns, and it does: grouped findings, urgency ordering, and the four fields each finding carries. What it leaves unclear is how `limit` (problems shown in full) and `detail` (brief vs full) interact with the grouping, so an agent cannot predict truncation behavior.

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

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

Schema coverage is 100%, so the baseline is 3; the description earns an extra point by giving `symptom` real meaning beyond the schema's 'what you see going wrong, in plain words' — it explains that the value is matched against lessons, with a concrete example ('helicopter bounces on the moving deck'). The remaining parameters (path, files, godot, limit, detail) are left entirely to the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource — runs the review, optionally loads every script and scene with Godot, groups findings by cause, orders them by urgency, and attaches place/lesson/fix/automation per finding. It explicitly distinguishes itself from godot_review (full list) and godot_check (raw Godot output), so an agent can pick it without opening schemas.

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

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

Opens with two concrete triggering conditions: a project you do not know yet, or something broken with no obvious starting point. Closes by naming the two alternatives and the condition that selects each, leaving nothing to inference.

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