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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=true, so the safety profile is covered; the description goes further with cost (10 credits per call, refunded if Géorisques is unavailable) and the three-state status model (available | no_match | unavailable). The remaining gap is that it doesn't say what happens on invalid coordinates or partial availability across the four signals.

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 front-loaded with the purpose, then a compact bulleted signal list, then constraints, then cost — a logical progression with no filler sentences. It is somewhat long, but nearly every line (status values, scope semantics, attribution duty) carries information the agent needs.

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?

There is no output schema, and the description compensates by describing the return payload in detail: status enum, spatial_scope (coordinate vs commune), provider classification and label, and a source URL. It also instructs the agent to surface source.attribution and source.update_date, which is exactly the post-call behavior an agent would otherwise miss.

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 coverage is 100%, so the baseline is 3, but the description adds meaningful domain constraints beyond the schema: WGS84, restricted to metropolitan France, Corsica or an overseas department, and it marks latitude/longitude as REQUIRED even though the schema has no required array. That compensates for a real schema omission.

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 opens with a specific verb and resource ("Get observed public geographic risk signals for a coordinate") and names the provider (Géorisques V2). It then enumerates the four returned signals by name, so an agent can distinguish this from siblings like analyze_dpe_price_and_thermal_risk or get_building_characteristics without opening the schema.

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 states explicit boundaries ("not a property diagnosis, not a regulatory risk statement (état des risques), no composite score. It never adjusts a valuation"), which tells the agent when NOT to use the output as a risk determination. It also gives a prerequisite/alternative path ("use resolve_location or the coordinates of a transaction first"), naming a real sibling.

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