CanWeShip Product Guidance

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.

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

Annotations already declare readOnly, idempotent and non-destructive, so the safety profile is covered. The description adds genuinely non-annotated context: the answer is 'preliminary', it arrives with claim-level source IDs and review dates, and FAWs/rule evidence/all sources are omitted by default and must be opted into via include — that default-vs-optional behavior is exactly the kind of disclosure an agent needs.

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 purpose is front-loaded in the first clause, and the two short follow-on sentences handle input tolerance and the default/opt-in split. The middle enumeration of returned content is dense but every item is a distinct payload component, so it earns its place; only minor tightening is possible.

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?

There is no output schema, so the description must carry the return shape, and it does: claim-level source IDs, check_product-compatible facts, carrier context, review dates and cited sources. Together with the input tolerance note and the include opt-in, an agent has everything needed to call it and interpret the result.

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 a baseline of 3 applies, but the description adds meaning beyond the schema: it explains that slug tolerates slugs, named products and aliases (matching the schema's examples but framing the tolerance explicitly), and it characterizes include as an opt-in for material that is otherwise withheld, which the enum list alone does not convey.

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 clause gives a specific verb and resource with scope ('Get preliminary U.S. domestic shipping guidance for one product'), which is far more informative than the title alone. It also lists the return contents, so an agent knows what it gets. It stops short of explicitly contrasting itself with list_products or check_product, so it falls just below the top mark.

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 rather than stated: the description says the response includes 'the facts check_product accepts', hinting at the get-then-check workflow, but never says when to call this versus list_products. The include clause does give actionable guidance on when to request extras ('left out unless requested with include'), which is real, if narrow, when-to-use advice.

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

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

Annotations already declare readOnly, idempotent, non-destructive, closed-world behavior, so the safety profile is covered. The description adds real value beyond that by specifying the shape of returned records (first sentence, verification date, guide URL) and that named products indicate which product check answers for them. It stops short of noting result limits or pagination, which is the remaining gap for a list operation.

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 what is returned before the parameter guidance, with no filler. The second sentence is dense but each clause contributes new information about search behavior.

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?

With only one optional parameter, no output schema, and rich annotations, the definition covers purpose, return contents, and search semantics well enough to invoke correctly. Minor omissions are result-volume behavior and an explicit pointer to the sibling check tools.

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% and the query parameter is already documented with examples, so the baseline would be 3. The description nonetheless adds meaning the schema lacks: query searches product names, aliases, and named products, and named products resolve to a specific product check.

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 opens with a specific verb+resource ('List the products CanWeShip checks') and even characterizes each result (first sentence of its answer, verification date, guide URL). It does not explicitly contrast itself with check_product or get_product_guidance, so the agent must infer that this is the browsing/listing entry point rather than the per-product check.

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?

The second sentence explains what passing query does and gives concrete examples, which implies the browsing use case. There is no explicit when-to-use-this-vs-check_product guidance, no statement that omitting query lists everything, and no exclusions, leaving the sibling routing to inference.

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