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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so safety is covered. The description still adds real behavioral context beyond that: it is a multi-stage composite ('enchaîne unité foncière, scénarios d'usage et bilan'), which tells the agent to expect a longer, aggregate run than a single-step tool. It does not disclose cost/latency implications of lire_reglement_ecrit or the 12-parcel fan-out.

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?

Three short sentences, front-loaded with the business question, then the outputs, then the input modes and pipeline. No boilerplate and nothing that could be cut without losing 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?

For an 11-parameter composite tool with nested objects and an output schema, the description conveys the pipeline, the two input paths and the sibling relationship, while the schema handles per-parameter detail and the output schema handles return values. The only gap is that it does not hint at how the optional bilan levers (prix_terrain_eur, marge_promoteur_pct, ecart_rendement_bps) change the outcome.

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 91%, so the schema already explains the eleven parameters including the enum and nested parcel object. The description only restates the two input modes ('Adresse ou 1 à 12 parcelles'), which duplicates the maxItems=12 constraint and adds little interpretive value.

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 names a concrete decision resource ('constructibilité, meilleur usage et bilan (marge, TRI)') framed as the question it answers ('Que peut-on construire ici et jusqu'à combien payer le foncier'), and explicitly positions itself relative to the sibling toise_bilan_operation ('moteur de toise_bilan_operation'), so an agent can tell it is the end-to-end orchestrator rather than the bilan engine itself.

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 gives clear context for invocation: one call replaces chaining unité foncière, scénarios d'usage and bilan, and inputs can be either an address or 1 to 12 parcels. It never states when NOT to use it or when to call toise_bilan_operation directly instead, so the alternative-routing rule is left implicit.

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