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

Annotations mark this as a non-read-only, non-idempotent operation, and the description supplies the missing context: it 'Records that the play ended in a reveal,' disclosing the state side effect. It does not address what happens on a repeated call, which matters given idempotentHint=false, so it stops short of full disclosure.

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?

Two sentences, no filler. The return contents come first and the precondition follows, matching how an agent needs the information ordered.

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?

There is no output schema, but the description enumerates what comes back (culprit, motive, clues, character outcomes) and notes the recorded side effect, so nothing essential is missing for a 3-parameter tool.

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 real meaning to gave_up by tying it to the 'gives up / wants the answer without accusing' scenario rather than leaving it as a bare boolean. slug and play_id are left entirely to the schema, which already documents them.

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 ('Returns the full solution of a Plot Speaks mystery') and enumerates the payload (who did it, why, clues, character fates). This clearly separates it from siblings like check_accusation or game_answer, which handle accusation logic rather than the full solution.

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?

Gives an explicit gating rule: only after the player has accused someone, or when they give up / ask for the reveal, and maps that second case to gave_up: true. An agent knows exactly when this tool becomes legal to call.

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