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

Annotations already communicate readOnly, idempotent, and non-destructive behavior. The description adds the geocoding source (Base Adresse Nationale), the return of one or more parcels with IDU, and the follow-up call to get_parcelle, which is useful behavioral context beyond the annotations. It does not say how ambiguity or no-match geocoding is handled.

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?

Three short sentences carry the entire message: purpose, output and downstream use, and input guidance. There is no filler and the most important information is front-loaded.

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 one-parameter, read-only tool with rich annotations, the description covers the input format, expected output (parcels with IDU), and the next tool in the chain. It omits explicit failure or empty-result behavior, but that is a minor gap for such a simple tool.

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?

The schema fully documents the single 'address' parameter with an example, so the baseline is 3. The description adds value by recommending the most complete address format (numéro, rue, commune), which improves geocoding precision.

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 gives a specific action and resource: geocode a French postal address with the Base Adresse Nationale and return the corresponding cadastral parcels with their IDU. It is clear and distinct from get_parcelle because it points to get_parcelle as a later step, but it does not explicitly contrast itself with sibling tools like find_parcelles_by_criteria or search_parcelles.

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 establishes a clear use case: an agent with a postal address should call this tool to obtain cadastral parcels and the IDU. It also instructs the caller to provide the most complete address possible (numéro, rue, commune). It lacks explicit when-not-to-use or alternative routing, so it stops short of a 5.

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