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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds meaningful behavioral context beyond annotations: the address input format, the fallback behavior when no street number is provided, the breadth of data returned, and the note that the text mirrors the road-page .md documentation.

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 packs a lot of useful content into a single dense run-on sentence, which is informative but hard to scan. The list of fact categories earns its place, and the input caveat is valuable, but the structure could be improved with clearer separation between scope and usage notes.

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 broad facts endpoint with no output schema, the description enumerates the major content areas and an important edge-case behavior. It is comprehensive enough for an agent to select the tool and understand what kind of data to expect, though it does not describe the response format or field naming.

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%, and the schema already gives a clear example for the address parameter. The description adds the important semantic nuance that the number is optional and that omitting it shifts the response to the road reference point, which is not fully captured in the schema.

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 clearly identifies the tool as a broad facts-gathering endpoint for a French address, enumerating concrete data categories such as cadastral parcel, urban zoning, risks, terrain, permits, sales, diagnostics, schools, and companies. This distinguishes it from the sibling tools, which each focus on a narrower slice (permits, commune, parcel).

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?

The description gives useful input guidance ('address in full words; without a number, the response applies to the road reference point'), but it does not explicitly state when to use this tool versus siblings such as get_french_parcel or get_french_building_permits. The usage context is implied by the listed scope, not made explicit with alternatives or exclusions.

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