Resolve a Nigerian address to a postcode

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

Annotations already cover readOnly/openWorld/idempotent, and the description adds real behavioral value beyond them: the tiered precision model, the fact that the address text is forwarded to an external geocoder, and the fallback that returns a `question` to the user rather than a false-precise code. It does not add rate limits or auth context, but for a read-only resolver this is solid disclosure.

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?

Purpose is front-loaded, followed by the precision rule and the parameter-filling instruction. The opening clause ('only as precisely as the evidence allows') is slightly awkward but the whole thing is four tight sentences with little waste.

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?

An output schema exists, so return-shape explanation is unnecessary; the description still flags the `question` fallback, which is the key non-obvious output behavior. Combined with the precision tiers and param guidance, an agent has what it needs, with the main omission being sibling routing.

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 the baseline is 3, but the description meaningfully clarifies that `landmarks` and `geocode_queries` are agent-derived from reading the address rather than passed verbatim, and echoes the 'at' = address-is-the-landmark rule. That goes beyond the structured field text.

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 + resource ('Turn a described Nigerian address into a postcode') with the unique twist that output precision varies with evidence. The distinction from siblings like lookup_postcode and validate_postcode is implied by 'described address' vs a written code, though no sibling is named 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?

It explains the outcome tiers (full building code vs area prefix with a `question`) and instructs the agent to derive `landmarks` and `geocode_queries`, but it never states when to choose this over the four siblings (lookup_postcode, autocomplete_postcode, validate_postcode, find_postcode_at_location). Usage is implied rather than routed.

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