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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so safety is covered. The description adds real value by defining the post-run verdict semantics (clean vs warnings, with the specific log conditions — QEq CG failures, lost atoms, fix halt, missing end_marker — that trigger warnings), which no annotation conveys.

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?

A single dense sentence that front-loads the state enum and then the returned fields; there is no filler. It is listy rather than prose, but every clause carries information.

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 must describe the return payload, and it does so fairly thoroughly, including the verdict logic. What is missing is any indication of staleness/live-fetch behavior or whether failed/cancelled runs omit fields such as cost or exit code.

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?

One required parameter at 100% schema description coverage, so the schema already documents the job id format. The description adds no additional meaning about `id` and is not expected to at this coverage level, giving the baseline 3.

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 enumerates exactly what the tool returns (state, GPU, rate, billed seconds, cost, exit code, error, thermo lines, verdict), which makes the read-only status-fetch purpose unambiguous. It does not, however, name job_log or job_results even though it overlaps with them on thermo lines and results, so the agent must infer the boundary.

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?

There is no statement of when to call this versus job_log, job_results, or list_jobs, and no note about polling or freshness. The agent gets the payload contents but no routing guidance.

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