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

Annotations declare readOnlyHint=false, which is surprising for something framed as a preview, and the description does nothing to explain why (does it persist a preview record, consume the idempotency key, or mint a digest?). With 8 parameters including expected_draft_revision, expected_snapshot_sha256 and expected_send_payload_digest, the description conveys none of the staleness/concurrency semantics that clearly define this tool.

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 zero filler. It is efficient but on the terse side for a tool with this much hidden protocol, leaving the burden on schema archaeology.

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?

No output schema, 8 undocumented parameters, and a non-obvious write-ish annotation mean the description had to carry the load and does not. It never says what the preview returns (rendered document? digest? validation errors?) nor how it feeds the subsequent send call.

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 8 parameters, and the description adds no meaning for any of them. The three required concurrency/consistency fields and the recipient override fields are left entirely raw, so an agent cannot know what expected_draft_revision or expected_send_payload_digest are checked against.

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?

"Review the exact offer and recipient without sending" states a concrete verb (review/preview) and resource (offer + recipient), and the phrase "without sending" implicitly separates it from the send path. It stops short of naming the sibling it pairs with (yardstick_offers_send_bind), so differentiation is inferential rather than explicit.

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?

Use before sending is strongly implied by "without sending," but the description never states the prerequisite state (e.g., draft submitted for approval, revision current) or names send_bind as the follow-up action. An agent must guess that this is the mandatory pre-flight step.

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