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

Annotations cover safety (not read-only, idempotent, non-destructive), but the description adds the critical async behavior: 'Returns immediately—poll get_journey_run at pollAfterMs', which is not in annotations. It also guides idempotent retry ('Reuse the same requestId if retrying an uncertain call'), directly reinforcing idempotentHint with actionable instructions.

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 tightly packed sentences, each earning its place: start behavior, mode-dependent behavior, polling and retry instructions. Front-loaded with the core action and scoping constraint.

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?

For an async start-operation with an output schema and rich annotations, the description covers the key operational details: private run, mode semantics, resume prerequisite, async polling, and idempotent retry. Minor gap: doesn't mention what the return object contains, though the output schema covers this; still, it's a model example of a compact but complete run 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% and both parameters are documented with descriptions. The description adds only the retry context for requestId; it does not expand on journeyId semantics. Baseline 3 is appropriate since the schema already does the heavy lifting.

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: 'Start one private browser run.' The destination is clear and distinguishes it from get_journey_run (poll) and create_journey (define). It doesn't explicitly name siblings, but the scope of the operation is unambiguous.

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 concrete when-to-use guidance for journey modes ('Learning/review journeys are explored; active journeys replay approved memory') and an explicit prerequisite ('Resume a paused journey first'), which routes the agent to resume_journey. No explicit when-not-to-use beyond that.

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