recover_research_jobs

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

No annotations are provided, so the description carries full responsibility for behavioral disclosure. It explicitly states idempotency, the empty-list result when there is nothing to recover, and a subtle safety property: tasks running in background threads of the current process will not be mis-marked. This is strong transparency for a mutation-style tool.

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?

The description is very compact: two sentences, with the core purpose first and the edge-case/idempotency behavior second. There is no filler or redundant restating of the tool name.

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 zero-parameter maintenance tool, the description covers when to run it, what side effects it performs, and its idempotent behavior. The only minor gap is that it does not describe the return value on success, but there is no output schema and the side effect is fully specified.

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?

The tool has zero parameters and the schema confirms this with 100% coverage. With no parameters to document, the description does not need to add parameter-level semantics, so the baseline 4 applies.

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 (recover interrupted research jobs), a concrete state transition (running tasks left by a crash are marked as pending), and implies a re-run capability. This clearly distinguishes it from sibling tools like cancel_research_job or delete_research_job.

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 description clearly implies when to use the tool: after a process crash or when running tasks have lost their executor. It does not explicitly name alternatives or say when not to use it, but the recovery use case is specific enough to guide tool selection.

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