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

Annotations already declare readOnlyHint=true and destructiveHint=false, covering the safety profile. The description adds behavioral context by specifying the output includes median and 75th percentile, and that score_global can be used to situate a score. It does not describe side effects or error conditions, but given the read-only nature, that is acceptable. It adds some value beyond annotations without contradiction.

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 two short sentences, front-loaded with the core purpose and followed by an optional parameter hint. Every word adds value; there is no fluff or redundancy. It is efficient and well-structured for quick parsing.

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 gives the key return metrics (median, 75th percentile) but does not specify the exact response structure (e.g., object fields, nesting). It also does not clarify the expected format of 'secteur', which is a required parameter. Given the tool's simplicity, this is a minor gap, but for a complete agent experience, more detail on input format and output shape would be helpful.

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 0%, so the description must compensate. It explains the purpose of score_global (to position a score) but provides no details about the 'secteur' parameter—such as accepted values, format, or examples. There is no guidance on how to specify a sector (e.g., industry name, code). This leaves a significant gap for agents to know how to fill the required parameter correctly.

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 states the tool provides sector benchmarks with specific metrics (active patents, R&D, global score) and statistical values (median, 75th percentile). It is a noun phrase but unambiguous in intent. While it doesn't explicitly say 'retrieve' or 'get', the purpose is evident. It doesn't explicitly differentiate from siblings, but sibling names (e.g., identite_operateur, statut_services) are clearly different domains, so no confusion.

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 no guidance on when to use this tool versus alternatives. It mentions an optional parameter (score_global) for positioning a score, which is a parameter-level hint, but does not state conditions like 'use when sector benchmarks are needed' or exclude any scenarios. There is no mention of alternative tools or when not to use it.

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