route_capabilities

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

Annotations already mark the tool read-only and idempotent, and the description reinforces this with 'Read-only' and 'Routing never executes anything,' adding the crucial behavioral clarification that this is a planning step, not an action. This goes beyond the schema by explaining the non-execution trait and the follow-on step, which prevents misuse despite the annotations.

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?

Three sentences with no filler; the main action and output are front-loaded, the filter behavior is compressed into one sentence, and the critical non-execution disclaimer is placed last but clearly. Every sentence contributes a distinct piece of information.

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 listing the route plan's fields (selected capability, binding, kind, execution_owner, approval, confidence, reason, fallbacks), giving the agent an expectation of the response. It also covers the core invocation requirement (objective required, optional filters) and the next step (execute_capability). It doesn't explain the meaning of 'unified capability' or error cases, but for an 8-parameter planner, this is solid coverage.

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%, so the baseline is 3. The description's only parameter-specific addition is the general statement that optional filters narrow candidate selection, and it mentions max_fallbacks' default, which the schema already provides. It does not add new semantics for tags/kinds/binding/providers beyond their names.

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 ('Pick') and resource ('best unified capability'), then enumerates the exact route-plan fields returned. It explicitly distinguishes itself from execute_capability by stating it never executes, making its role clear among 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?

The description provides an explicit alternative: 'feed the selected_capability_id to execute_capability,' which tells an agent which sibling to use next. It also explains that optional filters narrow candidate catalogs, giving context for when to include parameters. It does not explicitly exclude other decision-planning siblings like plan_decision, so it falls short of full when/when-not coverage.

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