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

Annotations already establish readOnly/openWorld/idempotent/non-destructive, so the description only needs to add scope. It adds useful semantic context by stating what the draft vs deployed-version requests return (step graph vs deployed steps). No contradiction with annotations.

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, front-loaded with the action and variant behavior, ending with a terse discovery pointer. No filler or repeated schema 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?

Given the annotations cover safety and idempotency and an output schema exists for return values, the description covers the invocation path: which resource, which mode, and where to find IDs. It is complete for a read-only getter.

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 adds extra meaning by tying the version parameter to the two output modes (draft step graph vs deployed steps). The schema handles the enum and format details (workflow_, ws_, TEST/PRODUCTION), so the description doesn't need to repeat them.

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 retrieval operation ('Get a workflow') and clarifies the two payload variants: draft step graph vs deployed version's steps. The phrase '(workflows group)' and the pointer to list_workflows help distinguish it from sibling get/list tools. No ambiguity about resource or action.

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?

Explicitly guides discovery: 'Use list_workflows to discover IDs.' It also communicates the main mode choice through 'or one specific deployed version's steps via version,' so an agent knows when to supply the version parameter. It doesn't name exclusions or alternatives beyond list_workflows, but the context is clear.

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