Geocode with IGN Géoplateforme; defaults to commune 97411. Inspect fuzzy-match score and citycode. Read-only adapter. Cache 24h; stale replies are marked.
| Name | Required | Description | Default |
|---|---|---|---|
| q | Yes | ||
| limit | No | ||
| api_key | No | othernet agent token, used only by othernet authorization. Never sent to the government provider. | |
| city_code | No | INSEE commune code. Defaults to Saint-Denis, La Réunion (97411). | 97411 |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint/idempotentHint, so 'Read-only adapter' is largely redundant, but the description adds genuinely new behavior: a 24h cache and the fact that stale replies are flagged. That caching/staleness disclosure is exactly the kind of trait annotations do not 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?
Four short clauses, front-loaded with the provider and the default scope, with no filler sentences. It is telegraphic enough that 'Inspect fuzzy-match score and citycode' reads as a fragment rather than guidance, but nothing is wasted.
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 does partially cover returns (fuzzy-match score, citycode) and adds cache semantics, which is more than most. However, the required q parameter and limit bounds are left entirely to the schema, and no guidance is given on interpreting the fuzzy-match score it tells the agent to inspect.
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 only 50%: q (the required parameter) and limit have no descriptions anywhere. The description's only parameter-adjacent content is the 97411 default, which duplicates the city_code schema description verbatim, and a hint about output fields, not inputs. It does not compensate for the undocumented required parameter.
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?
States a specific verb (Geocode) and names the backing provider (IGN Géoplateforme), which is far more informative than the bare tool name. The address focus implicitly separates it from government_communes_search and government_enterprises_search, though it never names those siblings explicitly.
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 'defaults to commune 97411' note implies the tool is meant for address lookups within a commune scope, but there is no explicit when-to-use/when-not guidance and no routing to government_communes_search for plain commune queries. Usage is inferable rather than stated.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.