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

With readOnlyHint and idempotentHint already declared, the description goes well beyond them: it confirms 'Does not save the draft,' and discloses the actual decision rules — price must match amount and currency of an active product, stock must be one of three approved forms, specs must be covered by a saved value, and retired products do not cover anything. This is rich behavioral context an agent cannot get from annotations.

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?

Purpose is front-loaded in the first sentence and the rest is information-dense rule text. The enumerated spec-phrasing list is long and slightly repetitive with earlier sentences about specs, but nearly every clause adds a testable rule rather than filler.

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?

An output schema exists and the description references its outcome ('when verdict is rejected'), so return values need not be explained. The validation rules are thorough. The only gap is the absence of explicit parameter naming and when-to-use framing, minor for a two-parameter read-only check.

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 coverage is 0% for both parameters, so the description carries the burden. It implicitly conveys what each parameter means (draft = the copy being checked, storeId = the store whose active catalog and saved specs govern the check), but never names or distinguishes them explicitly, so an agent must infer the mapping.

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 and resource: checking draft shopping copy against active catalog products. The validation semantics (rejects specs, prices, stock levels the catalog does not allow) clearly distinguish it from save_product, get_store_catalog, and the other siblings, which are catalog/CRUD tools rather than validators.

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 is implied through the closing rule 'Do not deliver copy when verdict is rejected,' which tells the agent this is a pre-delivery gate. However, no alternative tool is named and there is no explicit when-to-use/when-not guidance (e.g., relative to save_product or get_store_catalog).

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