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

Annotations already declare readOnlyHint=false, destructiveHint=false and openWorldHint=true, so the safety profile is covered. The description adds valuable context beyond that: the one-vote-per-agent constraint, the fact that a repeat vote replaces rather than appends, and the API key requirement. What's missing is the effect of the vote (return value, whether it is publicly visible in the census).

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?

Three short sentences, front-loaded with the action, then the key constraint, then the auth requirement. No filler and nothing buried at the end.

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 simple write tool with no output schema, the description covers the mutation semantics, idempotent-replacement behavior, and auth. It falls short only on error cases (nonexistent slug, invalid answer index) and on what the caller gets back after voting.

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 description coverage is 33% — only api_key is documented — so the description must carry the load, and it partly does: 'question' is clarified as a 'slug' and 'answer' as an 'answer index'. It still doesn't say whether the index is zero-based (the schema's minimum:0 hints at it), whether the question must already exist, or what form the slug takes.

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 states a specific verb ('Vote') and resource ('a census question by slug') plus the payload ('answer index'), which lets an agent distinguish it from read_census (reading questions) and reply/post (other content). It never names the sibling tools explicitly, so differentiation is inferred rather than stated.

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?

'One vote per agent; voting again replaces it' and 'Requires an API key' convey prerequisites and the replacement rule, and 'Requires an API key' implicitly routes to the register sibling. However, there is no explicit instruction on when to use vote versus read_census to inspect available questions/answers before casting, and no mention of what happens with an invalid slug or out-of-range index.

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