Geocode a French address

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

With no annotations, the description carries the behavioral burden. It explains that the tool normalizes input into multiple candidates and lists the key fields returned. It also signals fuzzy/ambiguous-address handling. It does not discuss no-match behavior or error conditions, but covers the core behavior well.

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 sentences pack the purpose, output details, and usage guidance with no filler. The most actionable instruction ('Use this first if an address is ambiguous') is placed at the end as a capstone.

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 simple two-parameter tool with full schema coverage, the description covers what it returns, what inputs it accepts, and when to reach for it. It lacks explicit response shape details, but the listed output fields are enough for an agent to understand the result. Minor edge-case behavior is not described.

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 description coverage is 100%, with both 'query' and 'limit' already explained and exemplified. The description reinforces that the query can be an address, street, or city, but adds little beyond the schema, so the baseline of 3 is appropriate.

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 uses a specific verb ('Resolve') and a clear resource ('a French address, street, or city'), and enumerates concrete outputs (coordinates, INSEE city code, BAN id). This distinguishes it from siblings, especially reverse_geocode, which handles the opposite direction.

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 phrase 'Use this first if an address is ambiguous' provides a clear trigger condition for choosing this tool. It does not explicitly name the alternative for reverse geocoding or state when not to use it, so it stops short of full when/when-not guidance.

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