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

Annotations only declare openWorldHint=true and destructiveHint=false; the description adds genuinely useful behavior: output is returned decoded as a string and must be interpreted per content_type, each run returns a trace_summary of executed steps, and draft vs published runs are governed by the version parameter. No contradiction with the annotations — it neither overstates destructiveness nor hides it, though it stops short of warning about side effects.

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 sentences, each earning its place: the outcome contract, the draft-vs-published version behavior, and the debugging pointer. All essential guidance is front-loaded before the alternative tool is mentioned.

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 5-parameter execution tool with an output schema, the description covers the return contract, the draft-testing flow, and the debugging path, and the 100%-coverage schema fills in parameter details. The only notable omission is an explicit warning about side effects or cost of executing a workflow, which openWorldHint only weakly implies.

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 baseline of 3 applies; the description itself adds no per-parameter syntax beyond the schema. It does add cross-parameter flow context (version connects to create_workflow_version's return value; run_id connects to get_workflow_run_traces), but the schema already documents each parameter in detail, so the description adds only marginal value here.

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 and resource ('Run a workflow now') and enumerates the exact return payload (status, content_type, decoded output, trace_summary), which distinguishes it from read-only siblings like get_workflow and get_workflow_run_traces. The scope of what it does is unambiguous.

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 explicit when-to-use guidance: pass version=<n> to test an unpublished draft vs omit for the published version, and explicitly routes debugging to get_workflow_run_traces using the returned run_id. The datafile parameter description also defines the scenario (testing a $datafile-reading workflow without wrapping it in an endpoint), so there is no ambiguity about when this tool is appropriate.

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