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

With no annotations at all, the description carries the full burden of behavioral disclosure, and it delivers richly: it states exactly what the tool computes (sum of points, base/complementary split), the specific 1% maladie rule on the complementary share, per-leg plausibility checks, and that global confidence follows the weakest leg. It even cites legal and source-file references, which is exceptional transparency for a calculation tool.

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 every clause carries information: core function first, then the critical exclusion and workaround, then the confidence behavior, then provenance. It is front-loaded and contains no filler or tautological padding, even though it is on the longer side.

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 the complexity (multi-scheme consolidation), the absence of annotations, and the absence of an output schema, the description does a strong job of explaining the computation, edge cases, and how to supply missing legs. The main gap is that it never explicitly states the response shape (e.g., total_brut, total_net, confidence, per-leg detail), which an agent would otherwise have to infer.

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 baseline is already 3. The description adds meaningful conceptual context beyond the schema: it clarifies that regimes must be points-based, that pensions_fournies is the mechanism for non-points legs, and that the net layer depends on rfr. This enriches the parameter model without needing to restate syntax.

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 is specific and immediately identifies the tool's core function: computing a consolidated total pension by summing points-based regimes, splitting base/complementary, and applying the gross-to-net layer. It clearly differentiates itself from siblings by emphasizing 'multi-régimes' and limiting scope to 'régimes EN POINTS', a boundary not present in the sibling names.

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 explicit operational guidance: non-points regimes (CNAV, fonction publique) must be supplied via pensions_fournies, sourced from retraite_estimation or the RIS, to obtain a truly total figure. While this clearly routes around a known gap, it stops short of explicitly naming the sibling to use when only non-points regimes are available, so it earns a 4 rather than a 5.

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