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

The description supplies the one fact that matters most for a preview tool: the offer is untouched, which is extra reassurance beyond destructiveHint=false. There is a mild tension with readOnlyHint=false (the call is not classified as read-only, presumably because it may write audit or derived records), and the description says nothing about what the preview returns, whether it is safe to call repeatedly, or what a rescind would do to the offer downstream.

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?

A single front-loaded sentence with no filler, and the key safety guarantee is placed at the end where it reads as a constraint on the whole action. It is arguably too terse for a 4-parameter tool, but nothing in it is wasted.

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?

There is no output schema, and the description never says what the preview actually shows — the withdrawal wording, the generated candidate email body, validation warnings, or a diff against the current offer. For a preview tool whose entire value is its returned artifact, that is a significant omission on top of the undocumented required parameters.

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 description coverage is 0%, so the description carries the full burden. It only hints at one parameter via 'optional candidate email' (email_candidate); offer_id, request_id, and especially idempotency_key — which is required despite this being a preview — are left completely unexplained.

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 concrete action (review a withdrawal plus the optional candidate email) and a scope guarantee (no change to the offer), which is enough to tell it apart from the mutating sibling yardstick_offers_rescind_bind. It never names that sibling explicitly, so the preview-vs-commit distinction has to be inferred from the name and the 'without changing' qualifier.

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?

The phrase 'without changing the offer' implies this is the safe pre-flight step before an actual rescind, so when-to-use is reasonably implied. However, no alternative is named — neither yardstick_offers_rescind_bind as the follow-up nor yardstick_offers_cancel_revision or yardstick_offers_status as the ways to inspect offer state — so an agent must guess the workflow.

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