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

Annotations already declare readOnlyHint and openWorldHint, so the safety profile is covered. The description adds real behavioral value beyond that: data is live from the operators, results are deduplicated to one entry per route/direction at its nearest stop, sorted nearest first, and include the next two departures. It stops short of noting coverage gaps or fallbacks when a place can't be resolved, which keeps it from a 5.

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 answer is front-loaded in the first clause, and every sentence contributes something (coverage, dedup rule, output contents, exclusions, alternative). It is slightly dense and run-on, packing several clauses into one sentence, but there is no filler.

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 an output schema present, the description needn't restate return values, and annotations cover read-only/open-world. What remains — coverage boundaries, dedup semantics, and the sibling handoff to plan_trip — is all supplied, so an agent has everything needed to call it 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 100%, and the schema already documents both the place formats (name, address, 'lat,lon') and the language enum, so the description has little room to add. Its only semantic contribution is the clarifying 'No destination needed', which frames place as an origin-only lookup. Baseline 3 is appropriate when the schema does the heavy lifting.

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?

Opens with a specific verb+resource: 'What's leaving now from the MTR stations, bus stops and green minibus stops around a place in Hong Kong.' It names the coverage (MTR, buses, green minibus), the ordering (nearest first), and the unit of output (each route and direction once), which distinguishes it cleanly from plan_trip.

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?

Gives an explicit when-to-use trigger ('for "when's my bus" or "what leaves near here"'), an explicit exclusions list (trams, ferries and Light Rail aren't included), and routes the A-to-B case to the sibling plan_trip. Nothing is left to inference.

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