Reply to a job

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

Annotations declare non-read-only, non-destructive, closed-world, so the safety profile is already covered; the description usefully adds the write-scope/auth requirement and the behavioral claim that this resumption path preserves full history. It stops short of saying whether the call blocks until the run finishes or returns immediately with a job id.

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 sentences, no filler, and the primary action is front-loaded with the secondary resume use case immediately after. The auth note is a short trailing clause rather than buried prose.

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?

An output schema exists, so return values do not need explaining, and the rich schema carries parameter detail. What remains thin is invocation mechanics: whether this is synchronous, whether it creates a new run id, and how it relates to jobs_run for a fresh attempt.

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 all seven parameters incl. text length limits, file path restrictions, model enumeration, autoRun behavior and budget are already documented. The description only restates 'optionally with files attached', adding no semantics beyond the schema. 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 concrete verb+resource combo ('Send another message to a job') and adds a second distinct capability ('the way to resume a stuck or failed run with full history'). That contrast implicitly separates it from jobs_create (new job), jobs_run, and jobs_tail (read history only), so an agent can route without opening schemas.

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 use case beyond the obvious one: resuming a stuck or failed run with full history. It does not say when NOT to use it (e.g. use jobs_create for a new job, jobs_stop to cancel), but the context is clear enough to select correctly among the jobs_* siblings.

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