trinv-chercher-parcelle

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

With no annotations, the description carries the full burden. It discloses the typical two-step process and the prerequisite of knowing the INSEE code, which is useful behavioral context. It does not mention return behavior, error handling, or side effects, but for a search tool the disclosed information partially addresses transparency.

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 well-structured: a clear opening statement, a two-step numbered list, and two relevant examples. It is concise and front-loaded with the core purpose; the link and examples are useful without excessive bloat.

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?

The tool has no annotations or output schema, placing full responsibility on the description. It adequately covers the input process (commune and area) and necessary prerequisite (INSEE code), but it does not state what the tool returns, how results appear, or what happens when no matching parcel exists. For a search tool this is a significant but not fatal gap.

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?

Since schema coverage is 0%, the description must provide meaning. It clarifies that 'area' is in square meters and that the other parameter relates to identifying the commune, but it leaves ambiguity about whether 'fragment' expects a commune name or INSEE code. The examples use names (BEDOUS, BEURD), while the text emphasizes the INSEE code, creating uncertainty.

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 defines the tool as searching for cadastral parcels of a certain area within a French commune, with parameters for commune and area (in m²). It provides concrete example queries (e.g., 'Y a-t-il une parcelle de surface 247 m² dans BEDOUS'). It distinguishes from the sibling tool by focusing on parcels rather than communes, but does not explicitly name the alternative, so it falls short of full sibling differentiation.

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 outlines a two-phase workflow (specify the commune, then the area) and stresses knowing the INSEE code, giving implied usage guidance. However, it does not explicitly state when to use this tool over the sibling 'trinv-chercher-commune' or provide exclusions, leaving the comparison implicit.

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