mdl_reviews_vote

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

Goes beyond the annotations by disclosing the host-configured authentication requirement and restating that it mutates remote data, which justifies the readOnlyHint=false annotation. It misses the non-idempotent implication of idempotentHint=false — an agent cannot tell whether re-voting toggles or duplicates the vote.

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 clauses, action first, then auth requirement, then the mutation caution — no filler. Slightly telegraphic at the front ('Reviews: vote' reads like a label rather than a sentence), but nothing is wasted.

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?

Annotations cover the safety profile (write, open-world, non-idempotent), and the description adds the auth constraint and a usage gate, so the call is not reckless. Still missing for a mutation tool: the semantics of 'direction', whether the vote toggles, and any hint of the response, which matters since there is no output schema.

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 0% and the description supplies nothing about either parameter. 'direction' is a bare integer with no enum or documented value set, so the agent cannot know whether 1 means upvote or downvote — the single most important detail for this call. 'review_id' and its anyOf integer/string form are equally undocumented.

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 ('Reviews: vote'), enough for an agent to tell it apart from siblings like mdl_reviews_get, mdl_reviews_submit, and mdl_reviews_edit. It is terse and never clarifies what a 'vote' means (up vs down) or that it acts on a single review, but the core action is unambiguous.

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?

'Use only for an explicit user request' gives a real gating condition, which is more than the average sibling offers. However, it names no alternative (e.g., mdl_reviews_get to read vs this to vote) and gives no prerequisites beyond the auth note, so routing is only implied.

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