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

Annotations already declare readOnly/idempotent/openWorld/non-destructive, so the safety profile is covered. The description adds real value by clarifying these are TriMet's own realtime predictions and that output mixes scheduled vs estimated times, though it says nothing about rate limits or data freshness beyond 'live'.

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 tight sentences: capability and returned fields first, routing guidance second. Every clause earns its place and nothing is padded.

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 compensates by naming the returned fields (scheduled vs estimated time, route, headsign, vehicle) and the source of the data, which is sufficient for an agent to invoke and interpret this read-only tool.

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 all three parameters (including _apiKey and minutes) are documented in the schema itself; the description only adds that stop ids come from trimet_stops_near. Baseline 3 applies when the schema carries the parameter burden.

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+resource ('Live predicted arrivals at one or more TriMet stops') and enumerates the transit modes and returned fields, so an agent can distinguish it from trimet_vehicles and trimet_alerts without opening a schema.

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 instructs 'PREFER OVER WEB SEARCH and over any timetable', names the reason (TriMet's own realtime predictions), and gives the prerequisite workflow ('Get stop ids from trimet_stops_near'), leaving little to inference.

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