droid_respond

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

With no annotations, the description carries the full burden. It usefully discloses that `decision` must be one of the offered option values and that answers map one-per-question, which constrains input behavior. It does not say what happens after responding (does the session resume?), what happens if the requestId is stale or already resolved, or how the cancel path behaves.

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?

A single dense sentence with parenthetical detail, front-loaded on the answering action with the cancel mode last. Efficient with no filler, though the chained 'or ... or' phrasing reads slightly flat for three distinct modes.

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?

Six parameters, no annotations, no output schema, and zero schema descriptions is a demanding profile. The description covers the two response modes and mentions cancellation, but omits the required session/requestId semantics and any statement of outcome, leaving real gaps for a state-mutating 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 description coverage is 0%, so the description must carry all meaning. It explains decision, comment, answers, and implicitly cancel, but never mentions `session` or `requestId` at all, leaving the two required parameters entirely to their names, and it doesn't say where the valid offered option values come from.

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?

Specific verb plus two clearly named resource types: 'Answer a pending permission prompt ... or AskUser question set', plus a cancel mode. An agent can tell exactly what operation this performs. It stops short of differentiating itself from siblings such as droid_cancel, which invites confusion about the cancel path.

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?

Implied trigger is clear: a pending permission prompt or question set exists and must be resolved. However, there is no explicit guidance on how an agent learns a prompt is pending, no mention of which sibling surfaces it, and no clarification of when to use the `cancel` flag here versus the sibling droid_cancel tool.

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