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

readOnlyHint=true already establishes the safe-read profile, and the description adds value beyond it: the free-tier boundary, the premium exclusion, and that a second death is included when a spouse exists. These are behavioral facts not encoded in annotations or schema.

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 the core action and cardinality, then the free/premium boundary. Three short sentences with minimal waste, though the pricing boundary sentence could be trimmed slightly.

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 readOnlyHint annotations and an output schema present, the description needn't explain returns or safety. It covers scope, cardinality, and the free/premium limit, leaving only the scenario object shape unaddressed, which the nested schema partially handles.

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?

Top-level schema coverage is 0% (the 'scenarios' array itself is undocumented), but nested $defs fields carry descriptions and the description supplies the '1 à 5' cardinality limit that the schema does not enforce via maxItems. It adds partial meaning without explaining the scenario object structure.

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 1 à 5 scénarios de transmission') with concrete examples ('usufruit total vs quart en pleine propriété') that make the output kind evident. It does not, however, explicitly distinguish itself from siblings like simuler_droits_succession, leaving the agent to infer the boundary.

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?

Implies when the tool applies and draws a scope line ('analyse premium, hors de ce périmètre gratuit'), which is useful. But it never names an alternative tool or the condition that would route an agent to simuler_droits_succession or explorer_optimisations instead, so routing guidance is implicit only.

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