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

Annotations already declare readOnly, idempotent, non-destructive, and closed-world, so the safety profile is covered. The description adds real value beyond that: what fields come back (status, transcript, runtime, reference quality) and how to handle non-terminal states via poll_after_seconds.

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 short sentences, front-loaded with the core action and result fields, then polling guidance. No filler, though the final sentence ('Failed or expired jobs are not successful results') is slightly redundant with the status guidance.

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 no output schema, the description does the work of naming the returned fields and explaining polling behavior, which is what an agent needs. It could say a bit more about what 'reference quality' looks like, but nothing critical is missing for correct invocation.

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 job_id and access_token are already documented, including the pattern and the auth fallback. The description only echoes 'by job_id' without adding format or usage nuance, so 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 specific verb and resource ('Read a previously submitted job by job_id') and clarifies the result semantics. It implicitly distinguishes itself from submit_compute_job via 'previously submitted', but never names the sibling get_compute_status, so an agent must infer which read tool to use.

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 concrete operational guidance: wait poll_after_seconds for queued/running jobs, and treat failed/expired jobs as not-successful results. It stops short of explicitly contrasting with get_compute_status, so routing between the two read tools is left partly to inference.

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