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

Annotations already declare this is a non-read-only, non-destructive, closed-world write, so the safety profile is covered. The description adds genuinely useful context beyond that: the attestation is stored 'against the credential owner,' clarifying accountability and attribution. It does not say whether the call is idempotent, what happens if the page was already acknowledged, or what a failure looks like.

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?

Two short sentences, front-loaded with the action and followed by the consequence. Minor redundancy: 'a person has checked' and 'someone has actually read the page' restate the same idea, so the second sentence slightly repeats rather than extending.

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 single-parameter write with annotations covering safety and no output schema, the description supplies what matters: that this is a manual attestation, that it applies to pages missed by the automated check, and that it is recorded against the credential owner. Nothing an agent needs in order to invoke it correctly is missing.

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?

Only one parameter and the schema documents it fully ('Hosted page ID', uuid format), so the schema carries the load. The description adds nothing about the parameter itself and does not, for example, explain how to obtain a page_id (presumably from list-hosted-pages or get-hosted-page). Baseline 3 applies at 100% schema coverage.

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 ('Record') and resource ('that a person has checked a hosted page'), plus a distinguishing condition: the page 'the automated fact check never read.' An agent can tell this is a manual attestation rather than an automated result. It does not, however, name any of the nearby hosted-page siblings (reject-hosted-page, request-hosted-page-regeneration), so sibling differentiation is only implicit.

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 phrase 'a hosted page that the automated fact check never read' implies the triggering condition, but there is no explicit statement of when to call this versus reject-hosted-page or request-hosted-page-regeneration, and no prerequisites such as needing the page to be in a particular state. Usage is inferable, not spelled out.

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