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

Annotations indicate read-only, open-world, idempotent, non-destructive. The description adds that it explicitly reports empty feeds via 'limits[]' and provides an editorial look without inventing products. This is useful behavioral context beyond annotations, clarifying the tool's handling of empty results and honesty constraints.

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 concise (two sentences) and front-loads the main purpose. The empty-feed behavior is placed second. Every sentence contributes, though the wording is slightly abstract. No waste, but could be more concrete.

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 3 parameters, adequate schema coverage, output schema exists, and annotations are rich, the description covers key behavior (empty feed handling). However, it lacks specifics on return format, pagination, or how include_products modifies results. Given the tool's moderate complexity, a bit more detail would improve completeness.

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%, with descriptions for query and limit, but include_products lacks a description. The tool description does not add details about parameters beyond what schema already provides, but the schema covers most parameters adequately. The description implicitly hints at query as 'intention', which is already in the schema. No need to compensate significantly, but the missing include_products description leaves a minor gap.

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 states it searches for shopping leads based on intent, but it is vague about the exact resource (shopping items) and does not clearly differentiate from sibling tools like 'search' or 'recommend_look'. The verb is implicit ('cherche') and the resource is not explicitly named, leaving ambiguity.

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?

No explicit guidance on when to use this tool versus alternatives. It mentions handling an empty feed, but does not discuss scenarios like when to prefer recommend_look or search. The context signal of siblings is not leveraged to provide exclusions or alternatives.

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