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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=true, so the safety profile is covered by structured data. The description adds that each zone is defined by address or lat/lon plus a mode, and that results include both shared-inhabitant figures and uncovered-commune candidates, but it does not disclose compute cost, geocoding dependency for the adresse parameter, or the constraint that zones form the network under test.

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?

It is short and front-loads the core computation, which is good. However, the prose is telegraphic and elliptical ('et communes candidates couvertes par aucun', the fragment 'Aussi parts de marché (modèle de Huff).'), so brevity comes at the cost of readability rather than being purely efficient.

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 complex geo-analytical tool with nested objects and an output schema, the description does cover the two result families and the Huff option, so the essentials are present. It still leaves the relationship between the cannibalisation output and the network-gap ranking unexplained, and gives no hint that the zone list must represent the existing network versus candidates.

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 100%, so every parameter, including the nested zone modes and Huff object, is already documented. The description restates the zone composition ('adresse ou lat/lon et mode') and flags the Huff market-share usage, which is mild added value over the schema but does not explain tri, huff alpha/beta, or communes_candidates semantics beyond what is already structured.

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 the resource (cannibalisation between my stores and network gaps) and specifies what is computed: shared inhabitants between 2 to 10 points of sale plus candidate communes covered by none, with an optional Huff-model market-share output. It is specific about output content but never distinguishes this tool from plausible siblings such as toise_comparer_zones or toise_communes_cibles, 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?

There is no explicit when-to-use or when-not-to-use guidance and no named alternative. The only routing hint is the fragment 'Aussi parts de marché (modèle de Huff)', which suggests the tool can double as a market-share analysis, but the agent is not told when to prefer a dedicated study tool instead.

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