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

Annotations declare readOnlyHint=false, destructiveHint=true, idempotentHint=false, and openWorldHint=true, which is a surprising profile for a 'validate' endpoint that the description never explains or qualifies. It also omits the behavioral facts an agent needs for a POST task endpoint: that it creates a task, that results are retrieved asynchronously, and what resource/cost implications the non-idempotent, destructive hints imply.

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 sentences, reasonably front-loaded with the purpose, but the first two largely restate each other ('designed to validate structured JSON-LD data and Microdata' / 'obtain microdata ... and detailed results of its validation'). The final sentence is the only one carrying operational information, and it is the one that is unactionable.

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?

An output schema exists so return format need not be described, but for a mutation-style POST submission with annotations flagging destructive, non-idempotent behavior, the description supplies no task-lifecycle context, no routing guidance among the many sibling on-page endpoints, and no valid schema-level parameter detail. The picture an agent needs to invoke it correctly is incomplete.

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 explains none of the actual request body semantics: the array-of-task-objects shape and the required id/url fields are left entirely to the schema, which has low description coverage at the top level. Worse, it directs the agent to a validate_micromarkup parameter that is not part of the schema at all, adding noise rather than meaning.

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 names a specific verb (validate) and resource (structured JSON-LD data and Microdata) and states the outcome an agent obtains (microdata present on the target page plus validation results). It is distinguishable from siblings like duplicate_tags or content_parsing, though it never contrasts itself with them explicitly.

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 only usage guidance is 'set the validate_micromarkup parameter to true in the POST request to OnPage API', and that parameter does not appear anywhere in the input schema, so the instruction cannot be acted on from the structured fields. There is no statement of when to prefer this endpoint over sibling on-page endpoints or what prerequisites (task submission, page URL source) must be met.

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