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

Annotations already declare the write/destructive profile, and the description adds real value on top: the required review:prepare token (an auth prerequisite), the immutability of the created proposal, the fact that nothing is confirmed or published, and the returned confirmation URL. The one gap is that destructiveHint=true is never explained — the description never says what state is overwritten or consumed.

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?

Four sentences, no filler, with the core action and the token requirement front-loaded before the conditional field rules. The dense conditional clauses are compact but readable; 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 9-parameter tool with nested objects and no output schema, the description covers the return value (confirmation URL) and the hardest identity-branching logic, which is genuinely useful. It still leaves the required evidence_id, feedback, and incentivized parameters and the whole context block unexplained, which is a meaningful gap for a preparation 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 9 parameters (many nested), so the description must compensate and it only partly does: it explains the target.merchant_id/offering_id branching, merchant_name, merchant_website, offering reuse, and that ratings are optional and must not be guessed. evidence_id, feedback, incentivized, and the entire context object are left undocumented in both schema and description.

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 gives a specific verb and resource ("Prepare one immutable proposal under a review:prepare token") and implicitly separates itself from the publishing step with "This does not confirm or publish it." It does not, however, differentiate itself from the similarly named sibling preflight_review or get_preparation, which an agent must disambiguate on its own.

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?

Usage context is only implied: "does not confirm or publish" hints that submit_review comes later, but no explicit when-to-use statement or sibling routing is given. The conditional target-field rules (merchant_id alone, offering_id alone) are field-filling instructions rather than selection guidance, so the agent gets partial, mostly inferential direction.

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