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

Annotations already cover the safety profile (non-destructive, non-idempotent write), and the description adds genuinely new context: the record is owner-signed, a signature over the canonical statement is required, the action does not alter measurements, and it does not suppress payTo alerts. It omits what happens on repeat announcements of the same statement, which matters given idempotentHint=false.

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?

The cost marker and the core verb+object are front-loaded, and each sentence adds a distinct constraint with no filler. The telegraphic fragments ('A payTo alert is not suppressed') are compact but slightly cryptic without surrounding domain context.

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 7-parameter, non-idempotent write tool with no output schema and low schema coverage, the description covers ownership, signature, and side-effect boundaries. It still leaves open the response shape, the effect of announcing twice, and whether statements are appended or replace prior ones — gaps an agent would want closed before calling.

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 only 29%, so the description must carry weight; it does explain that sig_b64 signs the canonical statement and that the payload covers price, payTo, effective_at, and note, which is real added meaning. But it leaves the format of effective_at, the units/meaning of planned_price_usd, and the role of session and host unexplained beyond the thin schema hints.

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 names a specific action (posts) and a specific object (a planned price and/or payTo set plus signature over the canonical statement), which goes beyond the title's generic 'Seller statement'. The clause 'Does not change a measurement' implicitly separates it from measurement-writing siblings, but no sibling is named explicitly and terms like 'canonical statement' and 'payTo alert' assume domain knowledge.

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 signals the cost ('FREE'), the caller requirement ('Verified owner'), and one exclusion ('Does not change a measurement'), which implies when this is appropriate. However, it never states when to prefer it over sibling tools such as seller_self_check or preflight, nor outlines prerequisites like having an existing seller record to sign against.

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