Keep a lesson learned here

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

Annotations only declare non-read-only, idempotent, non-destructive, closed-world; the description adds substantially more: redaction of names/paths/links/emails/keys/source before storage, refusal for name-heavy lessons, dedup-by-title behavior, local-only storage never sent anywhere, and the error conditions (refused, learning off). This is behavior an agent cannot infer from the annotations.

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 core action and the payoff, with no filler sentences. It is a dense single block covering purpose, field guidance, privacy, dedup, side effects and return values — all relevant, though splitting privacy/return details would aid scanning.

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 nine parameters and no output schema, the description covers what is returned ('the stored lesson and what was replaced'), the failure modes, the privacy transformation, and the upsert rule. An agent has everything needed to call it correctly and interpret the result.

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, but the description adds guidance the schema lacks: write in general words, title is one line, fix is what to do instead, and `error` should be 'the Godot message as printed, kept as a template'. It also states which fields are optional and worth filling 'when you can'.

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 — keep/store a lesson learned in this project — and distinguishes itself from godot_lessons (which shows lessons) and godot_check. The upsert semantics ('same title again updates that lesson') further sharpen what the call does.

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?

Explicitly says when to use it ('Add one whenever a fix took more than one try') and when not to ('not for what a review rule already reports'), and names the sibling tools whose output it feeds (godot_check, godot_lessons).

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