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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so the safety profile needs no restating. The description adds genuinely new behavior: data is sent to a named third party (Transitous) with stop ID and time, and no API key is required — a data-egress and auth disclosure that annotations cannot express. It stops short of describing fallback behavior when live predictions are unavailable.

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?

Four short sentences, front-loaded with the capability and ending with terse operational facts (Transitous, no API key). Nearly every clause earns its place; only the trailing "Omit departureTime for now" is under-specified rather than merely brief.

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?

There is no output schema, so the description usefully enumerates the return categories (live vs. scheduled times, cancellations, boarding restrictions) in place of one. For a nested-parameter read tool it is close to sufficient, with the undocumented `limit` and the ambiguous departureTime note as the remaining holes.

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 0% across three parameters including a nested stop object, so the description must carry the load. It does explain where stopId and the coordinates come from and gestures at departureTime, but it never mentions the nested `label` field or the `limit` parameter (default 10, max 20) at all, leaving a third of the surface undocumented in both schema and prose.

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 ("Show upcoming departures at a selected Bay Area transit stop") and enumerates what the payload contains: live predictions, scheduled times, cancellations, boarding restrictions. The Bay Area geographic scoping plus the pointer to search_places/plan_trip for the stop token separates it cleanly from the three siblings.

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?

Gives explicit prerequisite routing: obtain the stop ID and coordinates from a search_places STOP result or a plan_trip stop. That is real when-to-use guidance tied to named siblings. The one gap is "Omit departureTime for now," which reads as an incomplete caveat — an agent cannot tell whether the parameter is unsupported, ignored, or merely discouraged, so the exclusion is stated but not fully explained.

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