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

Annotations already declare destructiveHint=true and openWorldHint=true, but the description adds the substance behind them: the review becomes publicly visible to followers, an existing differently-worded review is left untouched unless replaceExisting is true, and a linked account is required. That is exactly the non-obvious consequence and auth context an agent needs, and it is not recoverable from the annotation flags.

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-loads the action and publication surface, then examples, then constraints and caveats – a sensible ordering with no filler sentences. The constraint sentence ('It takes 50 to 10,000 characters and a star rating, sent here or already on file') is the one tangled spot, compressing three separate facts into one clause.

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 an open-world destructive write with no output schema, it covers visibility, auth, conflict/no-op behavior, length bounds, and the sibling alternative – a solid package. The notable flaw is the stated '50 to 10,000 characters' floor against a schema minLength of 1, an inconsistency that could produce a surprise validation failure, and containsSpoilers is never mentioned in prose.

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?

With 80% schema coverage the baseline is 3, and the description earns a bump by clarifying that rating may be 'sent here or already on file' (i.e. genuinely optional despite being the semantic payload) and by explaining the replaceExisting no-op interaction. It adds nothing for containsSpoilers and leaves workId unexplained, but the schema covers containsSpoilers adequately.

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 ('Publish the linked reader's review of a book') and states the surface it lands on ('under their name on its siftivo.com page and to their followers'). It explicitly carves out the nearest ambiguous case with 'A star rating alone is add_to_library', so an agent can separate it from add_to_library and delete_review without opening a schema.

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 literal trigger phrasings ('post this as my review of X', 'change my review of X') plus an explicit exclusion routing to a named sibling ('A star rating alone is add_to_library'). The when-to-replace condition is also spelled out via replaceExisting, leaving nothing to inference.

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