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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so the safety profile is covered. The description adds genuine value beyond that by disclosing the tool is free and that it deliberately omits owners and valuation data. It says nothing about latency, coverage limits, or the multi-step address-confirmation behaviour implied by the schema, so it is a modest rather than rich addition.

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 short and front-loads the core question, with no filler sentences. However, it reads as a telegraphic list of fragments, the parenthetical asides are dense, and the trailing sentence about 'adresse' is unclear rather than economical — brevity at the cost of parseability.

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?

An output schema exists, so return values need not be described, and the annotation set covers safety. What is missing is input guidance for a 10-parameter tool at 30% coverage, particularly the address-confirmation flow and how the alternative locator parameters interact. For a tool this broad, the description leaves a real operational gap.

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?

With 10 parameters and only 30% schema description coverage, the description needs to carry weight but does not. It only names rayon_batiments_m — which the schema already documents — and never explains the choice between lat/lon, adresse, code_insee, section, parcelle_id and numero_parcelle, nor the adresse_confirmee/confirmer_adresse confirmation pair. An agent must infer the whole input strategy from the schema alone.

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 resource — a point/address fact sheet covering parcel, PLU zoning, easements, risks, surrounding buildings, taxes and indicators (Pinel, SRU, QPV) — and explicitly excludes owners and valuation, pointing those to toise_dossier_adresse. The verb is interrogative ('Que sait-on d'un point') rather than a crisp action verb, but the scope is 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 gives one useful routing rule (owners/value → toise_dossier_adresse) and flags that the tool is free, plus a cryptic workflow hint ('Inutile avant un outil qui accepte `adresse`'). There is no positive statement of when this is the right first call versus toise_indicateurs_territoire or toise_zonage_commune, and the final sentence is ambiguous enough that an agent may misread it as a prerequisite rather than a caution.

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