Pick contest winner

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

Annotations already declare destructive=true, non-idempotent, openWorld, so the safety profile is covered; the description still adds real value by stating the point-payout effect and, notably, honestly warning that the request body is undocumented and only presumed to be { "winnerId": "<option _id>" }. That caveat is exactly the kind of context annotations cannot convey.

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, front-loaded with the action and effect, then the body caveat. No filler; the only mild cost is the hedging 'presumably', which is justified given the genuinely undocumented payload.

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 a destructive, non-idempotent settle operation, the description says points are paid out but does not say whether the contest is auto-closed, whether the action can be undone, or what happens to losing bettors. Annotations cover the safety flags and there is no output schema to explain, so it is adequate but leaves real gaps around side effects.

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% (baseline 3), but the schema types the 'winner' body as a free-form object with additionalProperties, so it offers almost no semantic guidance. The description compensates with a concrete example body shape (winnerId -> option _id), which meaningfully reduces the guesswork for the one non-obvious parameter.

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 ('Settle a contest by choosing the winning outcome') plus the consequence ('pays out points'). Combined with the tool name, an agent can distinguish it from the sibling giveaways_draw_winner and from contests_close/contests_refund without opening a schema.

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?

Usage is only implied through the concept of settling a contest; there is no explicit statement of when to call this versus contests_close, contests_refund, or contests_bet, and no prerequisite (e.g., contest must be in a bettable/ended state) is given. Implied lifecycle context is present but no routing guidance.

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