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

Annotations already declare readOnly/idempotent/non-destructive/openWorld, so the safety profile is covered; the description adds real substance beyond that by disclosing data provenance (WithBy verdicts vs WSDOT's own words), differing depth per pass, and that every answer carries both the check time and the agency report time. It stops short of covering edge behavior, e.g. what happens for an unrecognized or misspelled pass name.

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?

Front-loaded with the usage trigger, then coverage, then output guarantees, then exclusions — a sensible order with no filler sentences. The sentence 'Covers Washington's mountain passes in depth, and the passes on the roads out of it, in their agency's words' restates coverage already given in the prior sentence and could be cut.

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 a single fully documented parameter, no output schema, and annotations covering safety/idempotency, the description supplies everything the agent needs: what is covered, which sources back which passes, and what each answer contains. Ambiguity handling for unknown pass names is the only remaining gap and is minor at this complexity.

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% and the schema already gives name examples, so the baseline is 3. The description earns a bump by enumerating the queryable set (Snoqualmie, Stevens, White, Blewett, the two bridges, plus 12 other passes), which helps the agent construct a valid 'pass' value; it does not explain matching behavior for ambiguous input.

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 opens with a concrete set of questions the tool answers (is the pass or I-90/SR 520 floating bridge open, what are the restrictions/chain rules, how long the crossing takes) and names the exact passes and bridges covered, so the resource and scope are unambiguous. It does not differentiate itself from the sibling 'passes_now', which by name sounds like an overlapping status tool, so the sibling distinction is left to inference.

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?

Trigger conditions are explicit ('Use this when someone asks whether...'), and there is a clear exclusion ('Not for navigation or bookings'). What is missing is the positive alternative: it never says when to prefer 'passes_now' or 'my_next_drive' instead, which matters given the near-duplicate sibling name.

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