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

No annotations are provided, so the description carries the full burden. It does add useful behavior ('detects stale running jobs and mark them retryable'), but it leaves ambiguity about whether resume actually re-executes the job or only marks it for retry, and it does not disclose side effects, idempotency, or behavior when called on a non-stalled job. Some value added, but meaningful gaps remain.

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 with zero filler: the first establishes the action and scope, the second earns its place by disclosing the resume mechanism. The purpose is front-loaded and the description is appropriately sized for a two-parameter tool.

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 state-changing tool with no output schema and no annotations, the description should clarify what the caller receives (e.g., updated job status or a new checkpoint) and what happens in edge cases like a non-stalled job. It covers the core operation but leaves the outcome and error behavior underspecified.

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 the baseline is 3. The schema itself already documents both parameters well, with jobId even referencing the sibling tools that produce it. The description adds no parameter-level detail, but none is needed given the schema's completeness.

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 states a specific action (Resume), a specific resource (harness job), and a specific scope (stalled or interrupted, from its last checkpoint). This clearly distinguishes it from the lifecycle siblings run_harness_job (start), plan_harness_job (plan), cancel_harness_job (stop), and get_harness_job (status). An agent can tell them apart without opening the schema.

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?

The condition for use is stated directly ('stalled or interrupted harness job'), which gives the agent clear context on when to call it. However, it does not name alternatives or give when-not guidance, such as 'to start a fresh run, use run_harness_job' or 'to abandon a job, use cancel_harness_job'. Sibling routing is left to inference.

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