cutbolt_job_resume

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

Annotations already cover idempotency and non-destructiveness, and the description adds real policy detail on top: only opted-in interrupted jobs within attempt limit are retried, and terminal jobs are excluded. It does not say whether reconciliation mutates the saved publication or how the drain is scheduled, so it stops short of full transparency.

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 that front-load the primary action followed by the retry scope and the exclusions. No filler, though the compressed domain vocabulary makes some clauses need a second read.

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 zero-required-parameter control tool with no output schema, the description covers effect, retry scope, and exclusions, which is most of what an agent needs. It omits what the call returns or whether draining is blocking/asynchronous, a minor gap given the tool's simplicity.

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% and the single parameter 'job_root' is documented there as the queue directory tied to render.start. The description never mentions it, so it adds no parameter meaning beyond what the schema already provides; baseline 3 applies.

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 specific verbs and effects: reconcile saved publication, wake the queue worker, drain queued jobs, retry opted-in interrupted jobs. This distinguishes it from cutbolt_job_start (launch new work) and cutbolt_job_wait (observe), though the domain phrase 'saved publication' is opaque without broader context.

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 defines which jobs are eligible ('explicitly opted-in interrupted retries within their saved attempt limit') and which are not ('Completed, cancelled and exhausted jobs are not rerun'), which implies usage. However there is no explicit guidance on when to prefer resume over cutbolt_job_start, job_wait, or job_status, or any prerequisite/precondition for calling it.

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