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

Beyond the annotations, it discloses the required `bookings:write` scope, that the first call is side-effect free, that unknown fields are refused by name, and that a summary plus confirm_token is returned. It does not state what the second call actually does externally (e.g., emails the client, given openWorldHint=true) or what happens if the confirm_token is stale, which is the main 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?

Three short sentences, front-loaded with the action and the required scope, with no filler. The middle sentence is dense and slightly tangled ("checks the arguments as the change would"), but every clause carries operational information.

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 non-idempotent mutation with no output schema, the description covers the confirm-token flow, precondition semantics, permissions, and validation behavior well. What it lacks is the nature of the outbound effect of sending and what the returned summary contains, which the absent output schema would otherwise have carried.

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?

The description adds real meaning for confirm_token (carry it over from the first response) and for the validation role of the first call, including the additionalProperties=false behavior of rejecting unlisted field names. proposal_id itself is never explained in either the description or schema, and expected_updated_at is only handled in the schema.

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?

"Send the offer" names a specific verb and resource, and the two-sentence body immediately clarifies that sending is a two-phase, preview-then-confirm operation rather than a single mutation. An agent can distinguish it from siblings like edit_offer or reject_offer, though the description never explicitly contrasts them.

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 concrete when-to-use guidance for the two calls: call once to validate and obtain a confirm_token, show the summary to the person, and only re-call with confirm_token after they agree. What is missing is routing guidance versus siblings (edit_offer, reject_offer, get_booking_proposal) when the offer needs changing instead of sending.

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