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

Annotations only declare the generic write/non-idempotent profile (readOnlyHint=false, idempotentHint=false), so the description carries real added value: it names the auth requirement (Bearer header), states which proofs actually count when matched, and discloses that payment_receipt is stored only as quarantined. This is meaningful behavioral context beyond the structured fields.

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?

Dense but front-loaded: purpose and product targeting come first, then auth, then proof semantics. Given the polymorphism and validation logic, most sentences earn their place; the run-on proof sentence could be split but is not wasteful.

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 complex polymorphic write tool with an output schema and rich nested schema descriptions, the definition covers the essentials an agent needs: what it does, auth, and the proof rules that determine success. Return values need not be described since an output schema exists. Minor gap is the meaning of outcome/reasons.

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?

Top-level schema description coverage is 0%, so the description must compensate, and it does explain the polymorphic 'proof' discriminator and the fields for shopify_order and email_receipt, plus product_id/product_url selection. It adds nothing about the 'outcome' or 'reasons' enums, but those values are largely self-explanatory. Adequate but incomplete.

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+resource ('Record a purchase outcome for a product') and identifies the two ways to target a product (product_id or product_url). It is clearly the write counterpart to the sibling get_product_outcomes, though it does not name that sibling explicitly. An agent can tell it apart from compare_products/search_products without opening the schema.

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?

Provides substantive context on proof types and how each is validated (shopify_order against the shop record, email_receipt by DKIM signature, payment_receipt quarantined), which guides which proof to supply. However, it never states when to use this tool versus alternatives, nor any preconditions beyond the API key. Usage is implied rather than delineated.

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