Answer a pending Harness approval or question

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

Annotations only say this is a non-idempotent, destructive, open-world write. The description adds substantive behavior: stale, duplicate, cross-run and cross-client replies are rejected; permission presets and permanent access are unaffected; write-vs-cancel outcomes are bounded. This is exactly the extra context the annotations cannot carry.

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 core action, then layered constraints in short declarative sentences with no filler. Slightly telegraphic and dense in the middle, but every sentence carries a distinct constraint that an agent needs.

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 three-parameter mutation with no output schema and 0% schema coverage, the description supplies authorization boundaries, rejection cases, and post-call continuation guidance. The remaining gap is that it never explains what runId must be or what the tool returns, minor given no output schema exists.

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 0%, so the description must compensate. It clarifies requestId semantics (must be a live id from list_run_interactions, exactly one) and the intent behind the response payload (approve-once, reject, ask the user), but says nothing about runId's role or the response oneOf discriminator shape, so the coverage is good rather than complete.

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 ('Resolve exactly one live requestId') and immediately anchors the resource to a sibling tool (list_run_interactions), so the agent can distinguish it from reply_run, steer_run, or cancel_run without opening schemas.

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?

Explicitly describes the decision procedure: grant allowed-once only within an already authorized task or after explicit user approval, otherwise reject or ask the user, never infer authority from child prompts. It also names the follow-up action (continue wait_run) and the alternatives it cannot handle (Windows UAC, policy=never), which is when-to-use guidance at the highest level.

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