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

Well beyond the annotations: it discloses staleness refusal semantics, refusal of anchors the page doesn't have, the 8-character minimum for quotes, that the page's author is notified, and the permission requirement. These are exactly the operational facts the readOnlyHint=false / destructiveHint=false annotations cannot convey.

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-loaded with the action and nearly every clause carries distinct information, but it reads as one long run-on paragraph mixing version, verdict, remarks schema and permissions; splitting the remarks anchor taxonomy into its own sentence would improve scanability without cutting content.

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?

No output schema and a stateful mutation with a nested JSON-string parameter, and the description covers the call mechanics thoroughly. It is slightly thin on what the returned review looks like or what state the review is left in after a partial write (no verdict), which would round out the lifecycle.

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 already 100%, so the baseline is 3, but the description materially enriches the remarks format that the schema only gestures at: the five anchor kinds, what 'key' means for each (heading anchor, theorem-block label, \label{...}), and what the quote must contain. It also explains the verdict lifecycle and reviewId's mode switch.

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?

Opens with a specific verb+resource ('REVIEW a wiki page') and immediately characterizes it as reviewing a proof/argument attributed to the caller's person, which separates it from add_wiki_comment or approve_wiki_page. The scope ('on the version you read') is stated up front.

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?

Explicitly tells the agent where 'version' comes from (get_wiki_page), that it is refused if the page changed, when to omit 'verdict' and later supply it with 'reviewId', when 'version' is not needed, and where the anchor keys come from (get_wiki_page_reviews' 'anchors'). The permission prerequisite ('Needs permission to comment on the page') is also stated.

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