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

Annotations already declare destructiveHint=true, idempotentHint=false and openWorldHint=true, yet the description adds meaningful context: the required bookings:write scope, the fact that the first call mutates nothing, unknown-field refusal by name, and the confirm_token handoff. It stops short of saying whether a rejection is reversible or what happens to the booking afterwards, which matters for a destructive mutation.

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 text is short, front-loaded with the action and permission, and the two-phase flow follows logically. A few clauses are compressed to the point of terseness ('Two calls', 'a field this tool does not take is refused, by name'), 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 three-parameter mutation with no output schema, the description covers auth, the dry-run precondition check, the human-confirmation requirement, and the shape of the first response (summary and confirm_token). Only the reversibility/aftermath of a rejection is left unstated.

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?

With schema description coverage at 67%, the schema already explains confirm_token and expected_updated_at. The description reinforces confirm_token ('same arguments plus confirm_token') but adds nothing about expected_updated_at or the required proposal_id, so the baseline 3 is appropriate.

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 opens with a specific verb plus resource ('Reject an offer') and immediately characterizes the operation as a two-call, non-destructive-first confirmation flow. It does not name the nearest siblings (edit_offer, decline_request, accept_request) to distinguish when each applies, so it falls short of a 5.

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 explicit procedural guidance: the first call changes nothing and only checks arguments, the summary must be shown to the person, and the second call happens only after agreement with the same arguments plus confirm_token. What is missing is guidance on when to choose this over edit_offer or other offer-related siblings.

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