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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the description correctly aligns with a read-only calculation. It adds the 'pédagogique' nuance but doesn't disclose specifics like return format, calculation frequency, or whether the projection is tabular or graphical. With annotations covering the safety profile, the description adds modest value but misses behavioral details an agent might need.

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?

A single, compact sentence that front-loads the purpose and lists the inputs. No filler or redundancy; every word earns its place. Perfectly sized for the tool's simplicity.

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?

For a tool with 4 parameters and no output schema, the description is too terse. It does not explain what the tool returns (e.g., a table, a number, a chart), how the calculation works (compounding frequency), or any input constraints (e.g., positive numbers, ranges). An agent could call it but might not know how to interpret results or validate inputs. The lack of these details makes the definition incomplete for real-world usage.

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. It maps the four parameters ('capital initial, versement mensuel, taux, durée') to the schema fields, but provides no additional semantics: it doesn't state that taux is annual percentage, that versement is monthly, or any units or constraints. The parameter names themselves hint at these, but the description adds only surface-level mapping, not deep meaning.

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 states a specific verb ('Projection') and a clear resource ('intérêts composés'), listing the key inputs (capital initial, versement mensuel, taux, durée). It is immediately distinguishable from all sibling tools, which are unrelated (PFU, content search, identity, phishing, product status, regulated savings rate). No ambiguity about what the tool does.

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 labels it as 'pédagogique', giving a clear context for when to use it (educational projection). It doesn't explicitly exclude alternatives, but since none of the siblings are similar, the usage context is sufficient. The lack of explicit when-not-to-use guidance is minor given the tool's unique scope.

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