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

Goes well beyond annotations: specifies no-op behavior and status code on no-op, that a real change writes history "unvote" and changed:["votes"], returns the full issue, and enumerates concrete error codes (403 viewer, 409 votes_disabled, 409 version_conflict with details.current). This is exactly the context annotations can't carry.

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?

Content is front-loaded and useful, but there is real duplication: 'idempotent' appears in the title and twice in the body, and 'Same rights ... and errors as vote_issue' is stated in both the first and second paragraph. It could be tightened by roughly a third without losing information.

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 4-param write tool with no output schema, everything an agent needs is present: preconditions (version), no-op semantics, side effects (history, changed), and the full error/retry story.

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%, so baseline is 3, but the description adds genuine semantics for `version`: where to source it (get_issue, list_comments, etc.) and the recovery protocol for 409 version_conflict, including the warning never to overwrite blindly.

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+resource ('Take your vote back', 'Removes the caller from `votes.by`') and is immediately distinguishable from its counterpart vote_issue, which it references by name.

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 the operative conditions: not having voted is a no-op (200, no new version), pass the `version` from get_issue, same rights/errors as vote_issue. It doesn't explicitly say 'use vote_issue to cast a vote instead', but the counterpart relationship is implied clearly enough.

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