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

Annotations cover the safety profile (readOnly, idempotent, non-destructive), so the bar is lower, yet the description adds real operational context: one search per origin regardless of destination count (cost shape), ambiguous names return candidates rather than guessing, addresses/coordinates are snapped to their nearest stop, planned timetable only with no live delays, and null where no connection exists.

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 core operation, then cleanly segmented into usage, inputs, output, and a worked example. Dense and well organized, though the illustrative 'which office site / which flat / how well a venue is connected' clause is mildly redundant with the preceding 'built for comparing locations'.

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 5-parameter, open-world, computed tool with an output schema, the description still supplies the return semantics (minutes[i][j], waiting for the first vehicle included, null for no connection) and the timetable caveat. Nothing needed to invoke it correctly is missing; transfer_time_factor is left to the schema, which documents it thoroughly.

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%, but the description adds meaning the schema lacks: the full accepted place grammar (stop name, address, named place, 'geo:lat,lon', find_place place_id), departure-time parsing rules (ISO 8601, offsets/Z converted, bare '08:00' means today or tomorrow if long past, omit for now), and the row/column meaning of the answer. This goes well beyond the terse schema strings.

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 ('compute the public-transport travel time... from each of several origins to each of several destinations'), plus scope (Switzerland, one departure time) and the matrix shape. It explicitly distinguishes itself from plan_journey and reachable_area, so an agent can route correctly without opening a 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?

'Use it when there are several places on either side' gives the positive condition, and it names the two alternatives with their selecting conditions: plan_journey for one pair with the actual connection, reachable_area for everywhere reachable. That is explicit when-to-use plus when-not-to-use routing.

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