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

Annotations already cover readOnly, idempotent, non-destructive and closed-world. The description adds real behavior beyond that: it prefers search_context to skip a second search, falls back to re-fetching the route, makes no bus-details calls, uses Azure OpenAI in-server, and accepts empty summaries when nothing differentiates. That is substantive disclosure, though it omits failure/timeout behavior.

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?

It is a single dense paragraph with the most decision-relevant fact ('Internal') front-loaded and no filler sentences. Some clauses are long, but each carries information an agent would otherwise have to infer.

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?

An output schema exists, so return values need not be explained, and the description conveys the call path and constraints well for a widget-driven tool. Still, for an 18-parameter interface with zero schema coverage, the near-total absence of parameter guidance leaves the invocation contract incomplete for anything but the widget that constructs the payload.

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?

With 18 parameters and 0% schema description coverage, the description carries the full burden but only addresses one input: search_context (its source and purpose). The remaining 17 parameters (trip_refs, cards, sort_by, price/rating filters, city ids, etc.) are undocumented in both schema and description. It does not compensate for the coverage gap.

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 states a concrete verb+resource: it builds 'differentiating one-liners' from the search payload, and it names the siblings it relates to (search_buses for search_context, no bus-details calls). The core purpose is clear, though the 'Internal: called by the widget' framing and Azure OpenAI mechanics somewhat bury the headline. An agent can tell what it produces, just not instantly.

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 'Internal: called by the bus-search widget after search results render' line implicitly signals this is not for direct agent invocation, which is useful routing context. However, it never states an explicit when-to-use vs alternatives for an agent, nor a clean 'do not call directly' instruction. Usage is implied rather than spelled out.

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