Resume a job paused for AI usage

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

Annotations already declare readOnlyHint=false, idempotentHint=true and destructiveHint=false, so the safety profile is covered. The description adds valuable context about the automatic self-resume at aiPause.resumesAt and provider-switching behavior, but says nothing about what happens if the job is not actually paused or what the call returns.

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 dense sentences with no filler, and the pause/resume context is front-loaded before the action. The phrasing 'aiPause in get_overview / wait_for_jobs' is slightly compressed but functional.

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, no-output-schema, well-annotated tool this covers the state model (pause, resumesAt, immediate retry) and the provider constraint. The only real gap is error/precondition behavior when the job is not paused, which is minor.

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%, so both parameters are already documented, giving a baseline of 3. The description does add meaning beyond the schema by explaining that provider means 'continue on this AI' and that pay-per-use API providers cannot be selected here, which is a real constraint the enum alone does not convey.

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?

The description uses the concrete action 'tries again now' on a job that is paused because its AI ran out of usage, which is a specific verb+resource. It also ties the tool to the aiPause state visible in get_overview / wait_for_jobs, distinguishing it from wait_for_jobs (which passively waits for the automatic resume).

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?

It establishes the trigger condition clearly: a job waits by itself until aiPause.resumesAt, and this tool attempts the retry immediately, implying 'use when you don't want to wait'. It also gives a usage constraint for the provider parameter (pay-per-use API providers can only be chosen in the app), but never states explicitly when not to call it or to prefer wait_for_jobs instead.

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