swiss_transport_gtfs_realtime

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

No annotations are provided, so the description carries the full burden of behavior disclosure. The description notes the API key requirement, which is useful, but doesn't disclose what happens without the key, the return format (GTFS-RT protobuf vs JSON), whether data is limited to Switzerland, or any latency/staleness characteristics of the real-time feed. For a real-time data tool with zero annotation coverage, behavioral expectations are under-specified.

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 a single efficient sentence that conveys the data source and the key prerequisite. There is no waste or redundancy, though it could be slightly improved with a brief note about feed types or output format without bloating.

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?

The tool is a single-parameter, no-output-schema, no-annotation tool that deals with real-time GTFS data. The description leaves significant gaps: no output format explanation (GTFS-RT feeds are typically protobuf binary, which agents may need to know), no authentication failure behavior, no refresh rate or data scope details. For a data-fetching tool, agents would benefit from knowing what to expect when invoking it.

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 single feed_type parameter is well-defined with an enum of three clear options (trip_updates, vehicle_positions, alerts). The description doesn't add semantic meaning beyond the schema, but each enum value is self-explanatory, so the baseline 3 is appropriate. No additional context about typical usage of each feed is provided.

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 the specific verb ('get') and resource ('real-time GTFS data from opentransportdata.swiss'), providing clear purpose. It distinguishes from sibling transport tools (station_search, stationboard, connections) which focus on static/near-time data, though it could more explicitly differentiate real-time feeds vs those alternatives.

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?

The description mentions a prerequisite (OTD_API_KEY env variable) but gives no when-to-use guidance or alternatives. It doesn't explain when to choose this tool over swiss_transport_stationboard, connections, or station_search, nor does it describe which feed_type to select for which scenario. The tool requires the API key setup but no exclusion criteria or comparison guidance is given.

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