ReturnCheck

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

With no annotations, the description carries the full burden and does so well: it discloses the verification behavior (quotes the exact clause verbatim, cites source URL, window/deadline, fees, confidence score), the anti-hallucination contract ('Never invents: returns UNKNOWN instead of guessing'), the cost caveat ('UNKNOWN is free'), and the measured server-side fetch hit rate. It also details the x402 payment path (call once free, read terms from structuredContent, re-call with payment_signature, and that UNKNOWN verdicts are never settled).

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 core question and the primary usage recommendation are front-loaded in the first sentence, and each sentence adds distinct information (fallback reliability, verdict format, no-guessing guarantee, payment mechanics). It is dense and longer than typical, with the payment details occupying substantial space, but no sentence is pure 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?

With no annotations and no output schema, the description compensates well by specifying what a result contains (verdict, verbatim clause, source URL, deadline, fees, confidence) and how failure is signaled (UNKNOWN, free). The remaining gap is that the role of the half-dozen optional inputs (reason, seller_name, item_condition, dates) in shaping the verdict is never explained.

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 67%, and the description adds real meaning for the most consequential params: page_text vs page_html tradeoffs (HTML allows JSON-LD structured data), page_source_url as caller-declared, unfetched provenance, and the full payment_signature workflow. However, several optional params (reason, merchant, seller_name, item_condition, dates) are neither described here nor in the schema, leaving their effect on the verdict unstated.

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 sentence states a precise, single-purpose question: 'can this specific product actually be returned?' and the description immediately enumerates the exact output verdicts (YES / YES_WITH_CONDITIONS / NO / UNKNOWN). There are no sibling tools to differentiate from, and the scope (one product, returns eligibility, with quoted policy clause) is unambiguous.

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?

It gives explicit optimal-use guidance ('BEST RESULTS: send the product page you already have as page_text (or page_html) along with product_url') and explains the consequence of not doing so (server-side fetch reaches policy for only ~1 in 3 US retailers, with the measured date and which retailer types are blocked). No alternatives or exclusions are named because none exist, so this is clear context rather than full when/when-not routing.

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