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

The annotations already disclose destructiveHint=true and readOnlyHint=false; the description earns credit by adding real behavioral context beyond them: a write-scope requirement and a hard precondition on resuming. It stops short of saying what error surfaces on refusal or whether the paused state is reversible through another path.

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 short clauses, front-loaded with the core action before the constraints. No filler or repetition, though the lowercase fragment style and the tacked-on scope sentence are slightly less polished than possible.

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 two-parameter mutation with full schema coverage, no output schema, and annotations covering the safety profile, the description supplies the key decision rule an agent needs. Only minor gaps remain: failure behavior on the refused resume and idempotency of repeated pauses.

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 the status enum is already documented, so the schema does the heavy lifting. The description adds marginal meaning by framing status as pause/resume and conversation_id as a single-conversation scope, but no format or edge-case detail beyond that. Baseline 3 is appropriate.

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 pair of verbs (pause/resume) and a precisely scoped resource: the responder for a single conversation. That distinguishes it from the responder-level siblings like configure_responder or get_responder, though it never names them. Clear and actionable without opening the schema.

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 an explicit when-and-when-not: pausing is allowed on any conversation, while resuming is refused after the person asked iris to stop. It does not route the agent to an alternative for the blocked case, nor mention the broader responder-configuration tool.

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