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

Annotations only declare the safe-read profile, but the description adds substantial behavioral context: replay-then-live semantics, the three termination conditions (run ends, 60 seconds, 200 events), the resume-token contract, and the auth scope needed. This is well beyond what the structured fields convey.

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 dense sentences, front-loaded with the operation and its streaming behavior, then the return shape, then the fallback and permission. No sentence is filler; each carries operational information the agent needs.

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?

There is no output schema, yet the description supplies the return shape ({live, cursor, events}), the termination rules, the resume path, and the authorization requirement. Nothing an agent needs to call and correctly interpret this tool is missing.

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 already 100%, so the baseline is 3, but the description adds meaning the schema lacks: it frames cursor as a resume token tied to the returned value ('resume with that cursor'), which clarifies the round-trip pattern. Minor note: it cites a 60-second live window while the schema defaults maxSeconds to 15, which slightly muddies the limit semantics.

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 names a specific verb and resource ('Watch a job's run') and immediately defines the mechanism: replay from cursor, then follow live. It also differentiates itself from the sibling jobs_get by naming it for the non-live case.

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 gives a clear conditional route: when the result is {live: false} there is no stream to attach to and the agent should read jobs_get instead. It also states the read-scope requirement. It does not contrast with other plausible siblings like jobs_continue, jobs_brief, or jobs_run, so it stops short of full when/when-not coverage.

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