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

Beyond the annotations (readOnlyHint, idempotentHint), the description discloses the computation layer: splitting base/complémentaire, applying the 1% maladie only on the complementary part, the gross-to-net activation via rfr, and the confidence model ('Chaque jambe est vraisemblance-vérifiée ; la confiance globale suit la jambe la plus faible'). It also cites sources for traceability. No contradiction with annotations.

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 each sentence carries distinct information: purpose, non-point routing, confidence behavior, entry-point warning, and sources. The key warning about double-counting is placed prominently. No filler; structure is coherent, though slightly long.

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 multi-regime pension calculator with no output schema, the description covers input strategy, routing, net calculation, and confidence aggregation. It does not specify the exact output fields (e.g., total_brut vs total_net vs detail), which is a minor gap given the absence of an output schema, but the confidence and non-point handling are explained.

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 coverage is 100%, so the baseline is 3. The description adds semantic context beyond the schema by explaining that pensions_fournies are legs not computed by the tool and are 'additionnées telles quelles, flaggées « fourni »', and that rfr activates the net calculation. This extra context helps the agent understand parameter intent, so a 4 is warranted.

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 opens with a specific verb and resource: 'Somme les régimes EN POINTS d'un relevé', and explicitly distinguishes from siblings by calling itself 'Point d'ENTRÉE pour une carrière multi-régimes' and warning against adding results of retraite_pension_regime. This makes the tool's role unmistakable.

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?

It states the primary use case ('Point d'ENTRÉE pour une carrière multi-régimes'), provides explicit routing for non-point regimes via pensions_fournies and names alternative tools (retraite_pension_annuites for fonction publique, retraite_estimation for CNAV), and includes a direct exclusion: 'ne pas y ajouter ensuite les résultats de retraite_pension_regime'. This gives an agent clear when-to-use and when-not-to guidance.

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