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

Annotations already cover the safety profile (readOnly, idempotent, closed-world, non-destructive), so the description earns credit for adding substance: delta direction, absence of aggregated net worth in the response, per-engine field-level scope, and the edge case that a blocked engine yields no computable delta. It stops short of 5 because it does not describe failure modes (e.g. mismatched engines, empty lists).

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 purpose, then inputs, then output semantics, followed by scoping caveats — a sensible order with no filler sentences. It is dense and somewhat run-on in the engine enumeration, but every clause carries information.

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 does real work explaining what comes back (per-engine deltas, no aggregated net worth) and what is out of scope. The remaining gap is that it never explains the response object's structure or where the input lists should originate, which matters for a comparison tool with 0% schema coverage.

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% and the schema is a bare array of free-form objects, so the description must carry the burden. It only restates that each parameter is 'une liste de résultats' and never specifies the required shape of a result object or which producing tool it should come from, though it does hint at the fields consumed (droitsNets, baseApresAbattement, droitsTotaux, valeurNuePropriete).

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 ('Compare deux listes de résultats Marcel déjà calculés') and the key differentiator versus the many simulate_* siblings — inputs are pre-computed results, not new simulations. It also specifies the direction of the comparison (B minus A). It does not name a specific sibling (e.g. compare_transmission, marcel_compare_scenarios) to route against, so it stops short of a 5.

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?

Usage context is implied by 'déjà calculés' and constrained by 'à moteur égal de chaque côté', and the description excludes some cases (donations progressives, assurance-vie hors succession). However, it never says which tool to use instead when scenarios are not yet computed, nor when to prefer compare_transmission or marcel_compare_scenarios over this one.

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