get_bus_arrival

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

Annotations declare readOnlyHint=true and openWorldHint=true, covering the safety profile. The description adds a list of valid stops and the behavior of omitting route, but doesn't describe return format, whether results are ordered by arrival time, or any live-data characteristics (refresh, latency). With readOnlyHint present, the bar is lower and the added stop list provides some context value.

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?

A single sentence with embedded useful parameter details — efficient and front-loaded with the main purpose. The stop list and route-omission note are valuable and compact. No filler or redundancy.

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 read-only query tool with no output schema and no required parameters, the description covers purpose, valid inputs, and key behavioral switches. It doesn't describe the return payload shape, which would be helpful since there's no output schema, but the read-only nature lowers the completeness burden.

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 carries the burden. It explains the stop parameter's valid values (8 named stops) and route's omission behavior, adding substantial meaning beyond the raw schema which only shows defaults. It does not clarify the route parameter's format (e.g., route number vs name), but covers the key semantics.

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 clearly states the tool queries real-time city bus arrival info at Kangwon National University stops, naming specific stops. The verb and resource are specific, but it doesn't distinguish from siblings like get_next_shuttle (which handles shuttle buses) — though the resource difference (city bus vs shuttle) is implicit.

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 lists valid stop values and notes that omitting route returns all routes. It does not explicitly state when to use this vs get_next_shuttle or other bus-related tools, nor when not to use it. Context is implied by the stops being city bus stops rather than shuttle stops.

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