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

Annotations already establish read-only, idempotent, non-destructive, closed-world behavior, and the description adds genuinely new behavioral detail: fuzzy station matching, recognition of London codes and nicknames (KX, TCR, E&C, ally pally), and the fact that twin stations like Hammersmith are returned separately. It stops short of describing ranking or ordering of results, but the matching behavior described goes well beyond the annotations.

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 purpose and input types are front-loaded, followed by the routing information. The parenthetical examples and the list of return types make the two sentences dense, but each clause adds useful information rather than restating the name.

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?

Given two parameters, full schema coverage, and an output schema, the description supplies everything an agent needs: what inputs are resolvable, how forgiving the matching is, what identifier formats come back (osm:…, uk:borough:…), and which sibling tools consume each result type. No behavioral gap remains for this tool's complexity.

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 adds real parameter-level meaning by showing that 'q' accepts informal inputs such as codes and nicknames, not just formal names, and by giving concrete examples of accepted place types. The 'limit' parameter (results per kind) is left to the schema.

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 opens with a specific verb and resource ('Resolve a place ... to ids') and enumerates the place kinds covered (station, borough, neighbourhood, postcode, street). It is clearly distinguishable from siblings like search_areas and find_areas because it states that the output is identifiers.

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 explicitly routes results to downstream tools ('for find_areas.near_stations', 'for find_areas.boroughs', 'for get_area_overview and assess_listing'), which tells the agent when this tool is the right precursor. It does not, however, state when to prefer search_areas or match_areas instead, so the alternative comparison is only implied.

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