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

Annotations already declare write/idempotent/non-destructive, so the bar is lower; the description adds real value by pinning the lifecycle state (draft only, no publish, no run) and the human-approval gate. It does not explain idempotency/retry semantics beyond what the requestId schema note covers.

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 short sentences, front-loaded with the gating precondition, and the second sentence delivers the key behavioral boundary. 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 an 11-parameter, deeply nested create tool, the description is thin: it explains intent but nothing about payload structure, required vs optional fields, or what 'complete' means. An output schema exists, so return values are covered, but the input side is largely unexplained.

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 only 9% (just requestId), with 11 parameters and a deeply nested 'map' object. The description says nothing about origin, name, period, purpose, department, or the required map structure, so it does not compensate for the schema gap.

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 ('Creates one draft' of a workflow) and clarifies the lifecycle boundary ('does not publish or run'). It implicitly separates itself from get_workflow/list_workflows, though it never names a sibling to route against.

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?

'Use this only after the user reviews and approves a complete conversation-drafted workflow' gives a clear precondition and an implied exclusion (unapproved or incomplete drafts). It stops short of naming an alternative tool for the non-approved case.

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