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

Annotations already declare readOnlyHint/openWorldHint=false/destructiveHint=false, and the description adds genuinely non-obvious behavior: the reminder comes back as full HTML in the response, with no file, no URL, no PDF, and nothing is dispatched. This tells the agent exactly what side effects to expect and how to handle the return value.

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 key constraints (scenario, output format, no dispatch) are front-loaded, but the exclusion of relance_impaye is stated twice in near-identical terms ('À ne pas confondre avec…' and 'Différent de relance_impaye (locatif)'), which is wasted repetition.

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 12 all-optional parameters fully documented in the schema and no output schema, the description supplies the missing piece — that the reminder is returned as inline HTML and not sent anywhere. It does not, however, address what happens with zero required parameters (e.g. defaults for montant_du, client_nom), which would have completed the picture.

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 100%, so the schema already carries the parameter meaning; the description only echoes the 1–4 level range. There is even a minor mismatch: the description names levels 1–3 while the schema allows up to 4. Baseline 3 applies since the schema does the heavy lifting.

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?

States a specific action (draft an invoice reminder for an unpaid artisan invoice in BTP) and explicitly distinguishes itself from the sibling relance_impaye (locative). The tool name, scenario, and level range (1–4) are all made concrete.

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?

Opens with the triggering condition ('QUAND un artisan n'est pas payé par SON client') and names the alternative tool with the reason not to confuse them ('relance_impaye, qui vise un locataire'). Explicit when-to-use and when-not-to-use routing.

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