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

With no annotations provided, the description carries full behavioral disclosure burden. It goes beyond a simple API summary to reveal meaningful behaviors: variant_id omission yields selection_metadata_not_offer options, only two sources per page are checked within a bounded 16-source window, results are not a stable snapshot, data retains golf-offer.v1, there are no member actions or click attribution, and deployment may return 503. This is rich, useful behavioral information.

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 description is compact but dense, with each sentence adding meaningful information. It front-loads the core purpose before caveats and edge cases. Some jargon like 'golf-offer.v1' and 'exact-source commerce gate' is unexplained, but the overall structure is organized and avoids redundancy.

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 the absence of annotations and output schema, the description supplies substantial context: usage prerequisites, variant behavior, pagination limits, result format version, and deployment failure mode. It is adequate for an agent to call the tool correctly, though a bit more detail on the actual shape of returned offers would push it to fully complete.

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 description coverage is 100%, so the baseline is 3. The description adds value beyond schema by clarifying the behavioral consequence of omitting variant_id on variant-bearing products and emphasizing that canonical_product_id comes from search_products. It also reinforces the meaning of offset within the bounded live window, enriching the schema's basic definitions.

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 clearly identifies the tool as discovering and verifying marketplace offers for a canonical product ID, using the verb 'discover' and 'verify' with a specific resource. It also distinguishes itself from siblings by describing the plural offer verification behavior and 'exact-source commerce gate', which is not present in sibling names like get_current_prices or get_verified_offer.

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 description provides clear context on when to use the tool: after getting a canonical_product_id from search_productsata, and when exact variant UUIDs are needed. It gives conditional guidance for variant-bearing products and advises to use next_offset for pagination. However, it does not explicitly state alternatives or when not to use this tool versus siblings like get_verified_offer or get_current_prices.

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