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

With no annotations, the description carries full burden. It explains the computation basis (last training, DDPP control, internal audit, PMS update) and the output (due date, urgency, recommended action), making it clear this is a read-only calculation. It also mentions the automation use case, adding behavioral context beyond a simple query.

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 front-loaded with the main purpose and provides essential details in four sentences, plus an English translation. It is appropriately sized for the complexity, though the bilingual duplication adds some length without redundancy in meaning.

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 description covers the purpose, inputs, computation logic, and output fields, which is sufficient for an agent to understand the tool. Minor gaps include the role of the optional department parameter (marked 'informatif' but used in frequency calculation) and default behavior when dates are missing, but overall it is complete enough.

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%, providing a baseline of 3. The description adds semantic value by explaining how each date is used (e.g., renewal interval, inspection frequency) and stating that type_etablissement is required while other dates are optional, enriching the schema with usage context.

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 it returns a calendar of upcoming HACCP obligations for an establishment, using the specific verb 'retourne' and identifying the resource. It distinguishes from sibling tools by focusing on the aggregated calendar based on last-action dates, with explicit details about the calculation inputs and output fields.

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 explicitly states it is designed for automation and suggests weekly calls to alert the manager, providing clear usage context. However, it does not explicitly compare itself to alternatives like get_formation_haccp_obligatoire or get_risque_inspection, so it falls short of a 5.

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