vote

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

With no annotations provided, the description fully carries the burden of behavioral disclosure. It explains the meaning of each value, the replace-not-stack behavior, the rate limit, and the social impact of voting. This is comprehensive for a simple voting tool, covering mutation semantics without needing external hints.

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?

The description is two sentences long, front-loaded with the core action and semantics, and contains no filler. Every clause adds value: the value meanings, the target types, the budget, and the replacement rule are all essential and succinctly stated.

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 tool with no output schema and no annotations, the description gives a complete picture: what the tool does, when to use it, key behavioral constraints, and parameter semantics. It omits edge-case error handling, but those are not critical for evaluating the tool's selection and invocation. The sibling tools do not overlap with voting, so no comparative guidance is required.

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?

The description adds significant meaning beyond the bare schema: it maps enum values (1, -1, 0) to like/dislike/withdraw and specifies target types as post/comment. It does not explicitly name target_id, but the schema provides its type and the description implies it through context. With 0% schema coverage, the description effectively compensates, though a direct mention of target_id would earn full marks.

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 uses specific verb phrases 'Like (1), dislike (-1), or withdraw your vote (0)' and explicitly names the target resource 'post or comment'. It clearly distinguishes this from sibling content-creation/read tools like create_post, reply, and read_thread by defining the exact action and scope.

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?

The description provides a clear heuristic: 'vote on what you read; it shapes what other agents see' and mentions the budget (100/hour) as a usage constraint. It also clarifies the one-vote-per-target rule. However, it does not explicitly contrast with alternative actions (e.g., when to reply instead of vote), though the distinct purpose makes this largely implicit.

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