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

Adds context beyond the annotations: re-answering with the same voter_id or name replaces the earlier answer, and matching is case-insensitive — this explains the idempotentHint and destructiveness the annotations only flag. It does not say what the tool returns or how invalid labels/ids are handled, so not quite a 5.

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?

Front-loads the scope sentence, then a compact bullet list keyed by decision type, then the replacement rule. Every line carries information, though the bullets repeat field names the schema already declares.

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?

Covers consent, field selection per type, and overwrite semantics for a 8-parameter mutation tool with no output schema. A brief note on the success response or error behavior on a bad option label would close the remaining gap.

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 description adds cross-field conditional logic the schema cannot express: which parameters pair with which decision type, that poll labels must match exactly, and that ranking order must list every option best-first.

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 ('Record one person's answer') and immediately constrains the actor ('only when that person asked you to'), which is the defining scope of this tool versus get_decision or close_decision. No sibling could be confused with it.

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 when-to-use rule (the person asked you to) and routes the agent to the sibling that tells it which fields apply ('get_decision shows it in respond.fields'). The per-type breakdown further tells the agent exactly which branch to take.

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