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

Adds genuinely non-annotated behavior: 'never fetches reviews', 'Unindexed products rank last', and 'This is not purchase advice'. The read-only/no-orders statement partly repeats readOnlyHint and destructiveHint=false, but the ranking and scope disclosures go beyond the annotation set.

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?

Front-loads the core action and scope, then layers usage routing, safety, edge behavior, and disclaimer in tight sentences with zero filler. Every sentence carries distinct information.

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 output schema, the description must explain results; it covers ranking order, the unindexed-last edge case, and read-only scope, which is enough to call it correctly. It stops short of describing the response payload shape, a minor gap for a tool with no output schema.

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 both the retailer enum and product_id formats are already documented. The description only echoes the '2-20' array bounds already encoded in minItems/maxItems, adding no new semantic detail; baseline 3 applies.

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 specific verbs (fetch Evidence Scores, rank) and the resource (2-20 retailer listings) ranked by GoBuy Evidence Score. It explicitly distinguishes itself from the sibling `check_product_trust` for single lookups, so an agent can separate the two without opening schemas.

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?

Names the triggering condition ('choosing between multiple products') and the explicit alternative for the adjacent case ('For a single product lookup, use `check_product_trust` instead'). The 'never fetches reviews' clause also implicitly routes review-analysis intent to the `analyze_reviews` sibling.

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