geocode_adresse

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

Annotations (readOnly, idempotent, etc.) are already present, and the description adds critical context beyond them: score ranges for reliability, the meaning of confidence_low, and the type hierarchy. No contradictions.

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?

Two well-structured paragraphs. The first is concise; the second contains necessary detail about output reliability. Slightly verbose but every sentence adds value.

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?

Covers the main geocoding behavior and output interpretation. Lacks error handling or what happens if address not found, but overall adequate for a simple geocoding tool with good annotations.

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 baseline is 3. The description adds value by explaining how the output fields (score, confidence_low, type) relate to usage, helping infer parameter influence. However, it does not explicitly detail the adresse format or examples.

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?

Explicitly states the tool geocodes French addresses to GPS coordinates, specifies the source (IGN Géoplateforme), and mentions precision at the house number level. This clearly distinguishes it from siblings like reverse_geocode and autocomplete_commune.

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?

Provides detailed guidance on interpreting the score and confidence_low fields to determine reliability, and explains the type granularity. However, it does not explicitly compare with alternative tools like autocomplete_commune or give when-not-to-use scenarios.

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