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

Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, destructiveHint=false. The description adds valuable context: update frequency (every 30 seconds), source (TfL Unified API), and licensing (CC-BY, no auth required). This goes beyond the annotations, improving the agent's understanding of data freshness and access requirements.

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 moderately lengthy but each sentence contributes: it states purpose, return fields, required parameters with examples, update frequency, filtering, and source. It front-loads the core purpose and maintains a logical flow. Some redundancy (e.g., repeating examples) is minor, but it remains concise enough for an agent to parse quickly.

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 schema is well-documented and an output schema exists, the description covers everything an agent needs: required parameters, return fields, sorting, filtering, data freshness, and access constraints. No critical behavioral gaps remain, making it safe for an agent to invoke without further clarification.

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 descriptions cover all parameters, so baseline is 3. The description adds concrete examples for line_id (central, bakerloo, etc.) and stop_id (940GZZLUHPK for Holland Park), and clarifies the NAPTAN format. It also explains the direction filter, adding usability without conflicting with 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?

The description clearly states the verb and resource: 'Get live arrival predictions for a specific TfL line at a London stop or station.' It specifies the return content (upcoming trains sorted by soonest arrival with destination, platform, direction, and minutes) and differentiates from sibling tools like tfl.transit.bike_points and tfl.transit.line_status by focusing on arrivals. The scope is unambiguous.

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 explains what parameters are required (line_id, stop_id) and how to use the direction filter, but does not explicitly compare with alternative tools (e.g., transport-rest.transit.departures). It implicitly targets TfL-specific data and provides clear usage context, but lacks explicit exclusion criteria for when not to use it.

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