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

Annotations already mark this as mutating (readOnlyHint=false) and non-destructive, but the description adds plan-check semantics for paid capabilities, the forced-private behavior of passwords, the refusal of public+password rather than silent resolution, and the invariance of URL/view count/content. This is rich behavior context that aligns with openWorldHint.

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?

Five sentences, each adding a distinct, necessary piece of information: core behavior, alternative, partial-update semantics, entitlement rule, conflict rule, and an exclusion with a pointer to the alternative. No fluff or repetition.

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 mutation tool with plan-dependent behavior, the description covers purpose, alternatives, edge cases, exclusions, and partial updates. The presence of an output schema means return-value description is unnecessary, and the only minor gap (permissions) is not critical given sibling context.

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 descriptions cover 80% of parameters, including rules for public, searchable, and removePassword. The description adds cross-parameter semantics: password forces private, public+password is refused, turning a paid capability off never requires entitlement, and only changed fields should be sent. This goes beyond the schema's per-property notes.

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 ('Change'), resource ('published page's settings'), and scope ('visibility, search-engine indexing or password'), and explicitly contrasts with deleting/republishing, which differentiates it from siblings like delete_page and publish. The title is equally clear.

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 instructs to use this instead of deleting and publishing again to preserve the shared link, and tells agents to send only changed fields. It also gives a when-not-to-use by declaring branding is not settable and points to get_page for brandingHidden.

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