find_stops

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

With no annotations, the description carries the full burden and does well: it discloses sort order (straight-line distance), the conditional default behaviour of radius_m (500m without query, unlimited with query), the limit cap of 50, and that results include serving lines. It stops short of stating read-only/safety semantics or how matching/pagination behaves at scale, but coverage is unusually strong for an unannotated tool.

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?

Front-loaded with the one-line purpose and the routing instruction, followed by a compact per-parameter block where each line adds distinct information. No filler sentences; even the Carris caveat earns its place by preventing wrong-tool use.

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 values need not be spelled out, and the description still flags the useful field (serving lines). Combined with full parameter documentation and the coverage caveat, an agent has everything needed to call this correctly.

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 0%, so the description must compensate and it does: every one of the five parameters is documented with matching semantics (accent/case-insensitive, all words must match, 6-digit stop id accepted), example queries, coordinate system (WGS84), defaults and max values for radius_m and limit.

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 and resource ('Find Carris Metropolitana bus stops') plus the two lookup modes (name and/or coordinate). It also names the downstream consumer (next_arrivals) and the sibling relationship, so the tool is distinguishable without opening its schema.

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?

Explicitly says 'Use this first whenever the user names a place, street, station or gives a location' and explains why (to get the stop_id needed by next_arrivals). It also adds a when-not caveat: Lisbon city buses are run by Carris, a different company not covered here.

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