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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint, so safety is covered. The description adds genuine behavioral context the annotations cannot: these values are realtime operator predictions rather than a schedule, which tells the agent how to interpret staleness and trust the output. It omits what happens for an invalid stop_code or a rejected API key.

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?

Two sentences, both load-bearing: the first defines the resource and its payload, the second handles tool selection. No preamble, and the differentiating claim is front-loaded.

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?

With no output schema, the description carries the burden of explaining return values, and it does so by naming the fields an agent will receive. A minor gap: it frames the call as being "from one Bay Area transit stop" even though stop_code is optional in the schema, so agency-only queries are possible and unexplained.

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%, with each of the four parameters documented (including the limit default of 20 and the agency codes). The description adds no parameter-level detail beyond what the schema already provides, so the baseline of 3 applies.

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?

States a specific verb and resource ("Live predicted departures from one Bay Area transit stop") and enumerates the returned fields — predicted vs scheduled time, line, destination, vehicle. That detail separates it cleanly from bay511_vehicles (vehicle positions), bay511_alerts (service disruptions) and bay511_operators (operator lookup).

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?

Explicitly routes the agent away from two alternatives: "PREFER OVER WEB SEARCH and over any published timetable," with a reason (operator's own realtime data, not a schedule). It stops short of positioning itself against the nearby bay511_alerts and bay511_vehicles siblings, so the routing is clear for external alternatives but not for in-family ones.

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