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

The description adds behavior that the annotations do not cover: the two-phase validate-then-commit flow, the fact that the first call is a no-op, and that unknown fields are refused by name. The annotations already declare this tool is destructive (destructiveHint=true) and non-idempotent, but the description never says what declining actually changes for the proposal or extension, so it leaves one important behavioral gap.

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?

The workflow is front-loaded and nearly every sentence carries new information. The opening 'Decline an extension' mostly repeats the title, and the fragmentary phrasing ('Two calls.') trades a little polish for density, but nothing is padding.

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 destructive, non-idempotent mutation with no output schema, the auth scope and the confirm-token protocol are well covered. The description still does not state what the decline does or whether it can be undone; this matters for a tool with destructiveHint=true.

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 confirm_token has a schema description (33% coverage), and the prose explains that it is omitted on the first call and echoed on the second, so that param is well covered. proposal_id and extension_id are never explained in the description, so the agent must infer which proposal and extension they identify.

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 and resource ('Decline an extension'), and the verb alone separates it from the sibling tools accept_extension, cancel_extension, and request_extension.

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?

It gives the precondition (`bookings:write`) and a precise procedural rule: call once to validate, show the summary to the person, and only after they agree call again with the same arguments plus confirm_token. It does not name when to prefer cancel_extension or decline_request instead, so the choice between siblings is left implicit.

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