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

Annotations already establish readOnly/idempotent/non-destructive/non-open-world, so the description correctly spends its words elsewhere. It adds two genuinely non-obvious behaviors: unknown or invalid facts are silently ignored and never count as clearance (a safety-critical fail-closed semantic), and next_questions is ordered the way the checker asks.

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?

Three tight sentences, each carrying distinct information: what it does, how to source the inputs, and the fail-closed/ordering behavior. The prerequisite sentence is front-loaded before the edge-case behavior, so an agent can act on it immediately.

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 3-parameter tool with a nested free-form object and no output schema, it covers input provenance, invalid-input handling, and one key return field. The gap is the response shape: besides next_questions it does not say whether carrier-specific failures, reasons, or a verdict field are returned, which matters given there is no output schema to fall back on.

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 100%, so the baseline is 3; the description earns an extra point by explaining where the `facts` keys come from (question ids from get_product_guidance) and what happens to bad keys (ignored). It adds nothing for `carriers` or `slug`, which the schema already documents well.

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 ('Evaluate') and resource ('supplied product facts') and pins the mechanism to 'the same deterministic USPS, UPS and FedEx rule runtime used by the CanWeShip checker'. It also signals output content ('next_questions lists the facts still open'), though the actual verdict/clearance result is only implied via the negation 'never treated as clearance'.

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?

Gives explicit sequencing guidance: 'Use the fact ids from get_product_guidance questions', which tells the agent to call the sibling first and how to key the facts object. It stops short of an explicit when-not-to-use statement or naming list_products as the entry point for slugs, so it is not a full 5.

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