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

Annotations already declare readOnly/idempotent/non-destructive, and the description goes beyond them with two operational facts an agent cannot infer: each store counts as one request against the rate limit, and fewer than two or more than five domains yields an error result. It also discloses the return shape per store.

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-loaded with purpose and usage before mechanics, with no filler sentences. The long parenthetical enumerating result fields is dense but substitutes for the absent output schema, so it earns its place, though it could be structured as a list.

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 covers return contents by reference to consulter_marchand, plus rate-limit cost and error conditions. For a 2-parameter read-only comparison tool, nothing an agent needs to invoke it correctly is missing.

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 baseline would be 3, but the description adds meaning not in the schema: the result order follows the input order, and out-of-range counts produce an error rather than being silently trimmed. The langue parameter's effect is left to the schema, which fully documents it.

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 names a specific verb and resource ("side-by-side test results for two to five French online stores") and fixes the ordering semantics ("in the order given"), which no sibling provides. An agent can distinguish it from classement_secteur and consulter_marchand without opening any schema.

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 states the selecting condition explicitly ("Use it when the user hesitates between specific stores") and routes candidate discovery to the alternatives by name: "To find candidates first, use trouver_marchands or rechercher_marchand." Both the when and the when-not are present.

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