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

Goes well beyond the annotations by disclosing that the original run is untouched, that outputs already recorded are reused, that only steps from from_step onward are executed and paid for, that unrecorded output is always re-run (never skipped), and that the new run records its parent run. It also flags the authentication requirement. This is exactly the extra context annotations leave out.

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?

Four sentences, all load-bearing, with the core action front-loaded and the cost/step semantics following. Slightly dense but 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?

For a mutation tool with no output schema, it covers auth, side effects on the original run, cost implications, and the meaning of the new run. The only omission is what the call returns (e.g. the new run id), though 'the new one records which run it continues' hints at it.

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 100%, so the baseline is 3; the description still adds meaning by clarifying the default behavior (resume at first step with no recorded output) and, crucially, that a never-recorded step is re-run rather than skipped — semantics not obvious from the schema.

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+resource ('Continue a stalled or finished workflow run from a chosen step') and immediately clarifies the mechanics by distinguishing it from a plain re-run: it starts a NEW run. An agent can tell it apart from run_workflow / advance_workflow / test_workflow_step from the text alone.

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 clear triggering conditions ('stalled or finished workflow run') and explains the omit-from_step default. It does not explicitly name sibling alternatives (e.g. run_workflow vs retry_workflow), so the routing is implied rather than spelled out, but the use case is unambiguous.

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