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

With no annotations, the description must carry the behavioral burden, and it does disclose two useful traits: warnings are emitted for missing mandatory mentions and values are never invented. However, it says nothing about whether anything is persisted, what the response looks like, or how the warnings are delivered, which matters for a tool whose name implies creation.

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?

One dense sentence that front-loads the core computation before the franchise rule and the warning behavior. Every clause carries information; only the parenthetical legal citation is arguably overhead for an agent.

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 has a deeply nested four-parameter schema, no output schema, and no annotations, so the description needs to explain the result shape and the role of the nested objects. It instead covers only the calculation and warning logic, leaving the agent guessing at output structure and the purpose of client/company/quote fields.

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, and it only partially does: it clarifies that VAT is grouped per rate and that the 293 B franchise is opt-in (mapping to company.franchise_293b). It leaves the client object, the entire quote object (number, date, validity_days, payment_terms), and required company fields (siren, address) unexplained.

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 gives a specific verb and object: it computes HT/VAT-by-rate/TTC totals for a French quote, applies the 293 B franchise, and raises warnings for missing mandatory mentions. That is considerably more precise than the bare name create_quote, but it never mentions building/returning the quote object itself (client, company, quote metadata), and it does not distinguish itself from render_quote_html.

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?

There is no statement of when to use this rather than get_legal_mentions or render_quote_html, even though those siblings clearly overlap (legal mentions, rendering). Only the conditional 'si demandée' for the franchise flag hints at a calling precondition; there are no exclusions or routing guidance.

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