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

Beyond annotations (readOnlyHint, idempotentHint), the description discloses meaningful behavioral details: each endpoint covers stops within a 300 m walk, board_stop indicates where to actually wait due to directional naming differences, and an empty options list signals the need for a transfer. It also clarifies ordering ('best first, walking counted'), adding real context beyond the safety hints.

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 description is information-dense without redundancy: it front-loads the primary function, then covers use case, behavior details, edge cases, prerequisites, and follow-up in a logical flow. Every sentence contributes a distinct piece of guidance.

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 the tool's complexityaint and existing output schema, the description covers all needed aspects: purpose, when to use, parameter acquisition, endpoint proximity behavior, empty-result meaning, and recommended follow-up. Nothing essential for correct invocation 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 coverage is 100%, so the baseline is 3, but the description adds practical semantics by telling the agent to obtain numeric stop IDs via search_stops or get_stops_around_location, and by explaining that each endpoint covers a radius of 300 m. This enriches the meaning of from_stop_id and to_stop_id beyond the schema's simple 'Stop ID' descriptions.

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 states a specific verb and resource ('Lists the direct routes (no transfer) from one place to another') and enumerates the returned details (board stop, get off stop, destination, stops in between, walking). It also differentiates from siblings by explicitly limiting to direct routes and defining the use case as 'how to get from A to B' or 'which bus/tram goes from one place to another'.

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 provides an explicit trigger: 'Use when the user asks how to get from A to B, or which bus/tram goes from one place to another.' It also gives prerequisites ('Requires numeric stop IDs; get them with search_stops or get_stops_around_location first') and a follow-up action ('Follow up with get_stop_realtime on board_stop for live departures'). It lacks an explicit when-not for transfers, though the empty-options behavior implies it.

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