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

Annotations cover the safety profile (idempotentHint true, destructiveHint false, readOnlyHint false), and the description adds real behavioral context beyond them: the job halts until resume_job, and the platform may pause/resume autonomously. No detail on error cases or interaction with the caller's own pause state.

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?

Two tight sentences with the core effect front-loaded. The second sentence about automatic pausing is relevant context, though slightly tangential to the tool's own contract.

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?

With an output schema present and annotations covering idempotency, the description only needs to convey effect and recovery, which it does. It stops short of describing what happens to already-queued work or how a manual pause interacts with a platform-initiated one.

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 job_id and idempotency_key are fully documented in the schema itself. The description adds no syntactic or semantic detail beyond that, matching the baseline for complete schemas.

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?

Names a specific verb (pause) and resource (job) and states the precise effect: no further execution until resume_job is called. This clearly distinguishes it from the sibling resume_job and cancel_job.

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?

Names the counterpart tool (resume_job) and explains that the platform also auto-pauses and auto-resumes on quota exhaustion or disconnection, which implicitly frames this as the manual, user-initiated pause. No explicit when-not guidance or preconditions are given.

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