Get Around Hong Kong

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

Annotations already declare readOnlyHint and openWorldHint, yet the description adds meaningful context: results are live (next departures, traffic delays), fares are charged in HKD regardless of the requested display currency, and the response embeds affiliate Klook ads. The affiliate disclosure in particular is behavior an agent could not infer from annotations or schema.

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-loads the routing purpose and packs the return contents into one dense sentence, with a short second sentence for the affiliate note. Efficient overall, though the first sentence is run-on and could be broken up for faster scanning.

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 and annotations covering the safety/open-world profile, the description need not explain return values or permissions, and the fully-covered schema carries the parameters. It is complete for calling the tool, with the only soft gap being cross-tool routing guidance.

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%, so the baseline is 3 — every one of the 12 parameters is already documented. The description only loosely reinforces this ('Octopus fares for the group' hints at the adults/children/seniors/disabled party-size params) without adding syntax or format detail beyond 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?

States a specific verb (routes) and resource (trip between two places in Hong Kong) and enumerates exactly what it returns: modes (MTR, bus, minibus, tram, ferry), times, legs with stops, fares, delays, map link. This is far more specific than the sibling search_place, which only resolves places, so an agent can tell them apart immediately.

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?

Usage is strongly implied by the near-self-explanatory purpose (route between two given places), but the description offers no explicit when-to-use, when-not, or relationship to search_place (e.g. resolving an ambiguous place name first). No prerequisites or exclusions are stated.

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

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; beyond that the description adds real behavior: results are ranked 'best first', the restaurant source is the official licence list, and passing `near` changes the ranking to nearest-branch-of-a-chain. With an output schema present it does not need to describe fields, and it does not.

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?

Two sentences, outcomes front-loaded ahead of the parameter tip, with essentially no filler. The first sentence is a dense list, but each enumerated place type adds genuine scope information rather than padding.

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 an output schema, readOnly/openWorld annotations, and 100% parameter coverage, the description supplies everything an agent still needs: search domain, result ordering, ranking override via `near`, and data sources. No critical decision-relevant information is missing.

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%, so the schema already documents query, near and language (including the enum). The description's restatement of `near` ('rank a chain's branches nearest to a point') adds only a small amount of intent, not syntax or edge-case detail, so the baseline 3 is right.

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?

It names a concrete verb (matching text) and a rich, specific resource set — stations, stops, landmarks, restaurants, buildings and street addresses in Hong Kong — plus result ordering ('best first') and payload content (type and coordinates). The only gap is that it never references the sibling plan_trip to draw a boundary, so differentiation is inferred rather than stated.

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 `near` condition for ranking a chain's branches by distance, which is genuine usage guidance. However, it never says when to prefer plan_trip over this tool, nor any exclusions (e.g. non-Hong Kong places, ambiguous queries), so the when-to-use-vs-alternative case is only implied.

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