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

Adds context well beyond the annotations: call/artifact paging happens 'without a new charge' (cost behavior), get returns a 'bounded status', cancel only affects 'pending dispatch' (scope of the destructive operation), and resume needs 'current authorization'. These disclosures are non-obvious and directly useful for safe invocation.

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, zero filler, with the action inventory front-loaded and the routing rule in the closing clause. Every phrase carries distinct 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 an output schema present and annotations covering safety, the description supplies the remaining essentials: all six actions, their scope, cost behavior, and the sibling routing rule. Nothing an agent needs to select or invoke this correctly is missing.

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 every parameter, including run_id/call_id/artifact_id requirements. The description adds only marginal tying of call_id and artifact_id to the call/artifact actions, so baseline 3 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?

Names a specific verb pair (inspect/control) and the exact resource class (runs started by workflow_run), then enumerates all six actions in verb+object form that map to the action enum. It explicitly separates itself from the sibling workflow_run ('use workflow_run to start one').

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 an explicit lifecycle boundary: 'Use for everything after a run is queued; use workflow_run to start one.' The alternative is named and the selecting condition is stated, and eligibility constraints are noted for resume ('eligible paused run with current authorization').

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