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

Beyond the annotations it discloses side effects: finalists become entries, the rest are hidden, voting opens, and it needs the organizer key. 'Can't be undone' is irreversible phrasing that sits in mild tension with destructiveHint=false, though nothing is deleted, only hidden. No pagination or return-value detail, which is acceptable given no output schema.

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?

It is front-loaded and dense with no filler. The 'Body: { finalists?: [post ids] }' fragment restates part of the schema, which is slightly redundant, but the sentence ordering (what it does, modes, consequences, auth) is easy to follow.

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 two-parameter, non-idempotent state-transition tool with no output schema, the description covers triggering modes, side effects on non-finalists, irreversibility, and authorization. Only the required contest-state precondition is left implicit.

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 50%, and the description compensates on the undocumented parameter: 'finalists?: [post ids]' says what the integers mean (post ids), that the field is optional, and that passing them approves a waiting suggestion. That is the key semantic an agent could not infer from 'array of integer'.

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 names a specific verb pair and resource state transition: 'close suggestions and start voting with the finalists'. That is clearly distinguishable from siblings like approve_all_posts or list_posts, which never open voting.

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 states the two calling modes explicitly – omit finalists to promote every approved suggestion, or pass them to promote only those – and notes that a waiting suggestion is approved when named. It stops short of naming an alternative tool or prerequisite state (e.g. contest must be in nomination phase).

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