set_expiry

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

With no annotations, the description carries the full burden, and it delivers: it discloses ceiling clamping with 409 expiry_clamped and 'nothing changed', the invariant that a shortened page can never be reported permanent, the acceptance of accept_clamp as the escape hatch, and the instruction to quote expires_at_iso rather than the requested value. This transforms a surprising, plan-dependent API into a predictable contract.

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?

Purpose is front-loaded in the first sentence and every subsequent clause conveys a load-bearing behavior or instruction; nothing is filler. However, it is one long monolithic paragraph mixing clamping, refusal, retry, and quoting rules, which could be clearer if split by scenario. Dense and efficient, but structurally improvable.

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 tool with no output schema and no annotations, the description covers the error contract, the retry flow, and the correct response field to use — remarkably complete for the tricky plan-dependent cases. The one real gap is id_or_slug, a required parameter whose target resource is never stated, forcing inference from the parameter name.

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 coverage is 0%, so the description must compensate. It does for two of three parameters: expires_in_hours ('hours-from-now' semantics, 'null for never', ceiling behavior) and accept_clamp ('take the ceiling'). However, id_or_slug — a required parameter — receives zero elaboration; the agent must infer from the name alone what resource it identifies.

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: 'Set hours-from-now expiry, or null for never.' This unambiguously states the operation, the resource, and the two allowed modes. No sibling handles expiry, so the tool is clearly differentiated from the site/client/share-link management tools around it.

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?

No sibling overlaps with expiry, so explicit exclusions are unnecessary. Instead the description gives scenario-based guidance: what to do when a number is clamped (response says so), what to do when null is refused (resend with accept_clamp: true or inform the user), and what value to quote. This is strong operational usage guidance, though it never states a generic 'when to use this tool' rule.

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