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

Beyond the annotations, which mark this as a non-read-only open-world write with destructiveHint=false, the description adds meaningful behavioral context: workflow runs attach verification.evidence and profileId, and the loop.line/initiate flag controls whether work continues. That is real post-invocation semantics an agent would not get from the annotations. It loses a point for leaving key terms like 'rank-1' and 'loop.line' undefined.

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 followed by the output-handling rule. There is no filler, but the dense internal jargon makes it less accessible than it could be.

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?

An output schema exists, so return values need not be explained. However, the description introduces concepts (loop.line, initiate, rank-1) that are not defined anywhere in the visible schema, and it never clarifies its relationship to plan_task or run_workflow, leaving an agent uncertain about the full workflow contract.

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 schema already documents all four parameters, including the goal/url guidance and the async behavior. The description adds essentially no parameter-level detail beyond what the schema provides, so the 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?

The description says it will 'Run a job from a plain-language goal,' which gives a verb and resource. However, 'job' is undefined, and it is never distinguished from siblings like plan_task, run_workflow, or run_playbook, except by saying one behavior is 'same as run_playbook.' Terms such as 'loop.line' and 'rank-1' are left unexplained, so the purpose is inferable but fuzzy.

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 does give procedural guidance for what to do after the call: read loop.line, stop if initiate is false, and otherwise apply rank-1 and then call verify_task. It does not say when to choose solve_task instead of plan_task or run_workflow, so the guidance is implied rather than explicit.

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