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

Annotations only declare readOnlyHint=false and idempotentHint=false; the description adds the materially important facts that the answer is bound to the caller's identity and cannot be changed after submission. That irreversibility is the key behavioral risk an agent needs before calling, and it is not derivable from the annotations alone.

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 constraint, then the norm. The immutability warning earns its place; the closing "Say what you actually do, not what sounds best" is a behavioral nudge rather than tool semantics and is mildly expendable.

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 three-parameter, fully schema-documented write with no output schema, the description covers what it does, the per-identity/immutable constraint, and the option format. Remaining gaps (what is returned, visibility of the answer to others) are minor for a tool this simple.

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 already 100%, so the baseline is 3, but the description adds a genuine disambiguation the schema lacks: option must be the number (e.g., 2), not the option text. That prevents a common invocation error and justifies going above baseline.

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?

"Answer one question as yourself" states a specific verb (answer) and resource (a single question in a poll), and the identity qualifier separates it from passive viewing tools like results. It is clear without opening the schema, though it does not explicitly name how it differs from propose.

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 implied rather than spelled out: the description constrains the act (one answer per identity per question, immutable) and implies prerequisites via the schema's "From list_polls" and "returned by enter" notes. It gives no explicit when-to-use versus propose/results guidance or exclusions.

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