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

Annotations already declare readOnly/non-destructive/idempotent/closed-world, and the description adds meaningful context beyond them: it performs no AI call, publishes nothing, and sanitizes HTML by removing active content. That sanitization/transformation behavior is a real disclosure. It stops short of describing how check failures are reported, so not a 5.

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 front-loaded sentences, purpose first, with zero filler. Every sentence carries distinct information (what, no-AI/no-publish, sanitization).

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 validation tool with a complex nested schema, no output schema, and 0% parameter coverage, the description omits what a failing check returns and how results are surfaced. The core 'what it does' is complete, but an agent lacks the surrounding detail needed to interpret outcomes.

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 with 3 parameters including a nested 20-field content object, the description must compensate but does not. It gives only a faint clue that 'body' holds HTML ('active content is removed') and never explains the plan or language enums or the content fields.

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 action (deterministic word/link/contact checks) on a specific resource (a manuscript), and explicitly distinguishes itself from the AI siblings via 'No AI provider call or publication.' An agent can tell it apart from ai_review_release/ai_adapt_release without opening either 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?

The 'No AI provider call' phrasing implicitly positions this as the non-AI validation alternative to the ai_* siblings, but it never states when to prefer it, ordering relative to ai_review_release, or prerequisites. Usage must be inferred.

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