Search Connections

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

Annotations already declare readOnlyHint=true, destructiveHint=false, and idempotentHint=true, indicating a safe, non-destructive read. The description adds valuable behavioral context: 'name resolution happens internally' (explaining input handling), 'Live data: includes delays and cancellations for trains departing within 30 min' (scope of real-time data), and the nuanced behavior of the 'arrival_time' parameter (defaults to departure time, only set true for explicit arrival requests). No contradictions with annotations.

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 paragraph but is well-structured and front-loaded with the main purpose. Every sentence adds value: input acceptance, return contents, live data scope, and parameter clarification. It is not overly long, though a slight restructuring could improve scanability. Overall, it is appropriately sized for the complexity.

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 5 parameters, no output schema, and sibling tools, the description is remarkably complete. It explains input formats, what is returned (times, duration, transfers, trip IDs), live data scope, and how to use parameters like 'arrival_time' correctly. It also hints at downstream usage (trip IDs for pricing/details/tickets). The description fully covers the tool's behavior without needing an output schema.

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 parameters are described in the input schema. The description adds significant semantic value beyond the schema: it clarifies that station names can be used directly (not just IDs), explains the 'arrival_time' parameter's default and when to override, and specifies that 'time' is treated as departure by default. This extra guidance is helpful for correct use.

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 'Find train connections between two Swiss stations', using a specific verb ('Find') and resource ('train connections'). It further specifies input flexibility (station names or UIC IDs) and output details (live schedules, delays, cancellations). This effectively differentiates from sibling tools like 'search_stations' (station search only) and 'get_trip_details' (details for a specific 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?

The description provides clear context: it accepts station names or IDs, returns live schedules, and mentions that live data includes delays for departures within 30 min. It also explains the behavior of the 'arrival_time' parameter and when to set it to true. However, it does not explicitly state when not to use this tool or recommend alternatives (e.g., 'get_more_connections' for pagination), so it misses some explicit guidance.

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