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

The description adds behavioral context beyond the annotations: it discloses that inputs are 'validated server-side,' returns an 'audited deliverable,' and mentions the reference case as an example. This complements the readOnlyHint and openWorldHint annotations. There is no contradiction; the 'returns' language matches the read-only expectation. It could disclose more about response format or cost, but given the annotations, the added details are sufficient.

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, with three sentences, and the key purpose is front-loaded. The reference case adds some specific context but is not excessive. It avoids unnecessary fluff, though the phrase 'Gapup agent-payable C-suite expertise' is a bit vague and could be clarified. Overall, it earns its place, but the reference case could be seen as optional.

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?

The tool is complex with 8 parameters, nested objects, and no output schema, yet the description provides little insight into what the report contains, how to structure the inputs, or what an 'audited deliverable' means in practice. It also omits any guidance on which fields are essential or how they influence the report. This is insufficient for a tool of this complexity, leaving the agent to rely on schema alone, which is sparse.

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?

Parameter schema coverage is only 13%, and the description does not compensate. It vaguely refers to 'documented case fields' without explaining any of the eight parameters, their relationships, or how to construct the nested 'company' and 'pillars' objects. Since the schema descriptions are minimal, the description should have supplied more semantic guidance but does not, making parameter understanding difficult.

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 produces a sustainability report ('Rapport de durabilité') and 'returns a structured, audited deliverable,' which identifies the verb (generate/return) and resource (sustainability report). However, it does not explicitly distinguish this from similar sibling tools like 'sustainability_reporting_pilot' or 'esg_audit_multi', so it lacks full sibling differentiation.

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 some usage context, such as 'agent-payable C-suite expertise' and a reference case, which implies a target audience and level of output. It also instructs to 'send the documented case fields,' but it does not explicitly state when to choose this tool over alternatives, nor does it mention any exclusions. The usage guidance is present but implied rather than explicit.

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