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

Annotations already declare destructiveHint=true, idempotentHint=true, and readOnlyHint=false, so the safety profile is covered. The description adds useful scoping context (blast radius limited to the previewed offer) but says nothing about what the rescind actually does to the offer, how binding-hash mismatches are rejected, or how resource_version_precondition failures surface.

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 scope constraint leads. It is efficient but arguably too sparse for a destructive multi-parameter bind operation, so content is under-specified rather than padded.

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, nested-binding tool with 5 parameters at 0% schema coverage and no output schema, one sentence is not enough. Missing are the preview prerequisite, how the binding object is populated from preview output, and the observable effect of a successful rescind.

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% across 5 parameters, including a nested binding object with five required fields (preview_hash, approved_action_key, approved_input_hash, approved_idempotency_key, resource_version_precondition) that are critical to a successful call. The description only hints that these values come from the preview, without stating that binding fields must echo preview output or what email_candidate/request_id do.

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 specific verb (withdraw) and resource (offer), plus a scope constraint limiting it to the offer reviewed in preview. It implicitly contrasts with the preview sibling without naming yardstick_offers_rescind_preview, so an agent can place it in the preview/bind pair but must infer the pairing from naming convention alone.

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 'only the offer explicitly reviewed in preview' implies the preview must be run first, but the prerequisite tool is not named and no explicit when-not-use or exclusion guidance is given, leaving the agent to infer the workflow from the *_preview sibling name.

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