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

With no annotations provided, the description carries the full burden and does well: it discloses that runnerID acts as this identity in its own browser, pauses for owner approval before anything risky, and returns immediately with a run_id (async). It doesn't cover failure modes, rate limits, or permissions, keeping it short of a 5.

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 tight sentences, front-loaded with the action and when to use it, then the behavioral contract, then the follow-up call. Every clause earns its place.

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 a 6-parameter async delegation tool with no output schema, the description covers the lifecycle (returns run_id, read via get_run) and the approval/identity behavior. It could say more about what happens on failure or approval denial, but an agent has enough to invoke and follow up correctly.

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 schema already documents every parameter. The description hints at identity usage ('as this identity') and result shape ('returns the result', 'call get_run'), but adds no syntax or format guidance beyond the schema, matching the baseline 3.

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 and resource ('hand ... a step you cannot finish') and even gives a concrete example ('work on a site you cannot sign in to'). It distinguishes itself from get_run by explicitly naming that sibling as the way to read results, giving an agent a clear mental model.

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?

Clearly signals when to reach for it (steps the agent cannot complete itself, e.g. authenticated sites) and routes result-reading to get_run. It stops short of explicit exclusions or listing other alternatives, but the context is unambiguous.

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