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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds genuinely new behavioral context: results are only indicative and are backed by 'cas de référence Marcel', which tells the agent how much to trust the figures, and it enumerates what is computed per associé. It does not state assumptions such as the fiscal year covered or the déficit foncier cap applied.

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?

Front-loaded with the purpose, then alternative, inputs, outputs and a caveat — a clean progression with no filler sentences. It is dense (long opening sentence) but every clause adds information an agent needs.

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 correctly supplies a return summary ('résultat et fiscalité par associé') and flags the indicative nature of results and the article 156 deficit limit. Missing pieces are the monetary unit and period, which matter for a numeric tax simulation, but otherwise it is sufficient to invoke the tool correctly.

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% on the top-level fields, so the description carries the burden; it partially meets it by naming the four inputs ('loyers, charges, intérêts, associés') and by referencing quote-part and tranche, which map to the nested tmi/quotePart fields. However it never states units (euros), whether amounts are annual or gross of anything, or that intérêts corresponds to interetsEmprunt, leaving real ambiguity.

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 verb and resource ('Calcule la fiscalité d'une SCI à l'impôt sur le revenu pour chaque associé'), plus the scope limit (2 à 5 associés) and the exact outputs computed (quote-part de résultat foncier, impôt, prélèvements sociaux, déficit foncier plafonné art. 156). It explicitly names the sibling it is not (simulate_sci_ir_vs_is), so an agent can distinguish it without opening either schema.

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?

Gives an explicit routing rule: for the IR vs IS comparison, use simulate_sci_ir_vs_is instead. The 2-to-5 associés constraint also implicitly scopes out single-owner cases. It stops short of stating when this tool should not be used at all (e.g. SCI à l'IS, or non-résident partners), so it falls one step below fully explicit guidance.

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