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

Adds real behavioral context beyond the annotations: finished steps and outputs are preserved and only unfinished work is re-attempted, plus quote=true is a no-op dry run. Does not address the idempotency risk hinted at by idempotentHint=false, but the preservation semantics are valuable and non-obvious.

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 tight sentences, front-loaded with the action and precondition, then behavioral guarantees, then the dry-run modifier. No filler.

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, return values need no explanation, and the description covers preconditions, mutation semantics, and the quote flag. Missing only the idempotency caveat and an explicit contrast with nearby run-control siblings.

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 coverage is 0%, so the description carries the burden and largely succeeds: it explains quote (prices the retry, changes nothing) and clarifies that revision must be the current one from get_workflow_run. run_id is left to inference but is self-evident from the tool name.

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?

States a specific verb (retry), resource (workflow run), and precondition (must be failed or canceled). The 'pick up where it stopped' framing is distinctive, though it never names the similar-sounding sibling resume_workflow_run to draw the contrast explicitly.

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 a clear condition for use (failed or canceled runs) and a prerequisite (revision from get_workflow_run). Lacks explicit when-not guidance versus resume_workflow_run or rewind_workflow_run, which are the closest alternatives.

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