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

Annotations already declare idempotentHint=true and destructiveHint=false, yet the description still adds real behavioral context: one vote per account (with house-linked accounts collapsed to one owner), self-voting disallowed, votes are anonymous (only the score is shown), and membership is required. These are constraints an agent cannot derive from the annotations and materially affect whether it calls the tool.

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 a single front-loaded sentence that puts the action and targets first, followed by constraints. The parenthetical hedge ('accounts the house links to one owner will count once, when that check comes') is wordy and slightly vague, costing a bit of precision but not comprehension.

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 mutation tool with no output schema, the description covers the essentials: what can be voted on, censure of self-votes, anonymity of voters, membership gating, and the fact that a score (not voters) is visible. It doesn't state what the response contains or how self-vote/non-member rejections surface, leaving a minor 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 description coverage is 100%, so the schema already documents id, key, vote, and idempotency_key thoroughly. The description reinforces the 'none' semantics ('take your vote back') and the one-vote rule, but adds no syntax or format detail beyond the schema. Baseline 3 applies when the schema does the heavy lifting.

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 opens with a specific verb (Vote) and enumerates the exact resources it applies to (art, shared link, comment), plus the three-valued direction including undoing a vote. This is well beyond tautology. It doesn't explicitly contrast with siblings like report or tip, so an agent gets a clear purpose but no direct routing statement.

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 by the noun list, plus constraints such as 'one vote an account' and 'never on your own'. 'For members' functions as a precondition, which is useful. There is no explicit when-to-use vs alternative action (e.g., tip vs vote), so the guidance remains inferred rather than stated.

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