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

Beyond the annotations, the description discloses the play_id dependency, the one-rating-per-play uniqueness constraint, and the minimum content requirement of stars or a verdict. It also notes that feedback is read by the people who make Plot Speaks. It does not describe what happens when a duplicate rating is submitted or what the call returns, but the annotations already cover mutability and idempotency signals.

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?

The description is front-loaded with the core action and then lists the rating components efficiently. It is a single dense sentence, which makes it slightly heavy to parse, but every clause (play_id, one rating per play, stars/verdict requirement) carries useful information.

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?

For an 8-parameter mutation tool with no output schema, the description covers the required story and play_id, the main rating fields, the verdict workflow, and the uniqueness constraint. The main gap is that the optional 'wish' parameter is not mentioned and no failure/duplicate behavior is described, but the schema fully documents all parameters and annotations cover the safety profile.

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 adds cross-parameter semantics not obvious from individual schema fields: the 'stars or a verdict (or both)' validation rule, the intended meaning of verdict for stories under test, and the spoiled flag as 'whether anything was given away too early.' It does not mention the 'wish' parameter, leaving that 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?

The description opens with a specific verb and resource: 'Saves a rating and feedback for a Plot Speaks story the user has just played.' It enumerates the rating content (stars, spoiled flag, comment, feedback, verdict), so an agent knows exactly what this tool records. It doesn't explicitly name a sibling such as review_story to distinguish scope, but the 'just played' / play_id framing implicitly separates it from story-writing tools.

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?

It gives concrete prerequisites and constraints: 'Needs the play id from start_story; one rating per play; stars or a verdict (or both).' It also conditions verdict use on 'a story still being tested.' It does not explicitly say when to use this tool versus review_story or write_story, so there is no exclusion guidance.

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