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

Annotations already cover the safety profile (readOnlyHint=true, destructiveHint=false, idempotentHint=true, openWorldHint=false). The description adds useful behavioral context beyond annotations: the décote is returned as a separate line (ligneDecote), quotePartImmo maps to the SCPI real-estate share, and the plafonnement uses the provided revenu fiscal de référence. It does not fully describe the output shape, but with no output schema it is reasonably transparent.

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 dense but front-loads purpose, then inputs, output, and special calculation rules. Every sentence earns its place, though the single-paragraph French structure could be more scannable with separation between inputs, outputs, and caveats.

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?

Given a complex tax simulation with no output schema, the description adequately covers purpose, required inputs, output value, and special rules (décote threshold, plafonnement). Annotations handle safety, and the schema handles structural validation; remaining gaps are detailed meanings of nested enum/boolean fields, which are minor for correct invocation.

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 supply parameter meaning. It lists the main top-level inputs and clarifies quotePartImmo for SCPI, but it omits details for nested fields such as the actif 'type' enum values, the passif 'deductible' flag, and the role of 'age'. It adds partial semantic value but does not fully compensate for the empty schema descriptions.

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 precise verb ('Calcule') and resource (IFI), with legal references and the exact components computed (assiette, barème, décote, plafonnement). An agent can immediately distinguish this from sibling simulations like simulate_av or simulate_pea.

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 gives clear context by naming the domain (IFI) and listing required inputs, which implies when the tool is relevant. However it does not explicitly state when to use it versus sibling tools, nor does it mention exclusions or alternatives.

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