Execute explicitly permitted workflow steps once; halt the chain when dependent queued work appears so evidence can be reviewed.
Execute explicit allowed steps once; dependent queued work stops the chain for evidence review.
| Name | Required | Description | Default |
|---|---|---|---|
| steps | Yes | ||
| run_id | Yes | ||
| workspace_id | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Changes observed during successful MCP inspections.
v0.3.1Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare destructiveHint=true and non-idempotent, so the safety profile is covered. The description adds that dependent queued work halts the chain pending evidence review, which is genuine behavioral context beyond annotations, though the mutation semantics (what gets destroyed by destructive steps) remain unstated.
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?
One sentence, front-loaded with the verb, and no wasted words. But the compression is so extreme that the sentence is under-specified rather than concise.
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?
A destructive, non-idempotent execution tool with three required parameters and zero schema coverage needs far more: prerequisites, what a steps entry looks like, and side effects. The output schema covers returns, but invocation correctness is not addressed.
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 0%, so the description carries the full burden and fails: workspace_id, run_id, and especially the required but untyped 'steps' array get no explanation of form, ordering, or per-step shape.
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 verb 'Execute' and resource 'steps' are present, but the scope is obscure: 'explicit allowed steps once' is cryptic without knowing what 'allowed' means. It is distinguishable from workflow.start only by inference, not by explicit statement.
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?
No statement of when to use this versus workflow.start or workflow.status. The clause about queued work stopping the chain is a behavioral detail, not usage guidance. An agent has to guess the selection rule.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.