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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, but the description adds genuine context beyond them: the full set of twelve decision codes, the rule-set version and source page for traceability, and the decision_id intended for downstream tools. It does not explain the credential parameter's auth role or whether the decision is cached/versioned per call.

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?

Two sentences, front-loaded with the purpose and the return contract, with no filler. The twelve-code enumeration is long but is the tool's actual return vocabulary, so it earns its space rather than being 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?

Given that an output schema exists and annotations cover the safety profile, the description is nearly complete: it names the inputs, the conditional inputs, and the decision_id chaining to downstream tools. The remaining gaps are the undocumented channel and credential parameters and the absence of any guidance on valid actor_class or market values.

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?

With 0% schema description coverage the description must carry all meaning, and it explains six of eight parameters: product (GTIN or catalogue id, optional), ship_to market, actor_class, and the conditional product_type/ingredients/claims trio. It leaves channel and credential completely unexplained, and gives no hint about the expected values or format for actor_class and ship_to.

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 opening 'Allow or deny, with the reason and the rule' states a specific decision action on a transaction, and the enumeration of twelve reason codes makes the tool's scope unmistakable. It is clearly distinguishable from narrower lookups like get_market_status or get_notification_requirements, though it never explicitly names those siblings as alternatives.

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?

There is real conditional guidance — the item identifier is optional and product_type, ingredients and claims are needed 'when no record exists yet' — which tells the agent how to shape a call. However, there is no statement of when to use this gate versus composing the individual lookup tools, and no prerequisites for the credential parameter.

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