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

Beyond the annotations, it discloses substantial behavior: the AI-described attributes (type, surface, roof, terrace, construction, style, readable brand), the return shape (a 'best' match with a claim of recognition, plus 6-9 alternative proposals with cheaper/larger/faster angles), the privacy guarantee that no image is retained, and a concrete rate limit of 10 analyses per day. This is exactly the kind of operational context annotations cannot carry.

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?

Front-loaded with the required input and its constraints, then the processing and return behavior, then privacy and rate limits. It is a dense single paragraph but each clause carries information; only the phantom image_type reference is wasted/misdirecting text.

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?

With no output schema, the description properly explains what comes back (best match plus 6-9 alternatives) and covers input constraints, privacy, and rate limits. The only completeness defect is the reference to a non-existent image_type parameter, which is inconsistent with the schema it ships with.

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 already 100%, so the schema documents image_url on its own; the description usefully adds format and 5 MB size limits. However, it references an 'image_type' value ('Si la photo montre un terrain, image_type vaut terrain') for a parameter that does not exist in the schema, which is misleading given additionalProperties=false and could cause a failed call.

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 states a specific verb+resource: take a photo URL, have AI describe the chalet, and return the closest catalog model plus 6-9 alternatives. This clearly differentiates it from siblings like find_chalets or search_chalets, which work from text/criteria rather than an image.

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 trigger is explicit and contextual: the user is showing a photo of a chalet ('une photo de chalet vue par l'utilisateur'), and the input constraints (public https URL, JPEG/PNG/WebP, 5 MB max) define when it can be called. It does not name alternatives such as find_chalets or compare_chalets, so the routing guidance stops short of full when-not instruction.

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