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

Annotations only mark it as a non-read-only, non-idempotent write; the description adds real behavioral context beyond that: the flow is ALWAYS created inactive, graph is validated on save, and certain node types are unavailable here. The inactive-by-default + mandatory review/enable cycle is exactly the kind of trait an agent cannot get from 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?

Front-loaded with the core action and the two modes, then the workflow. The middle sentence cataloguing what a flow can do (tag contacts, enroll in sequences, public comment replies) is dense and partly tangential to invoking this tool, costing some tightness.

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 6-param tool with nested objects and no output schema, it covers creation modes, validation, inactive default, scope limitations, and the follow-up workflow. It never hints at what the call returns (e.g. the new automation id), which is the main remaining gap.

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 83% (baseline 3), and the description still adds meaning: 'Without graph it creates an empty one to fill in later; with graph it validates and saves the whole thing' clarifies the graph parameter's two contracts. Trigger semantics are largely left to the schema, which already documents them thoroughly.

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?

Specific verb+resource ('Create a chatbot flow for the connected accounts') and it spells out the two creation modes (empty vs. validated full graph). It never names the obvious sibling create_automation_from_template, so the agent must infer the difference from context rather than being told.

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 an explicit post-creation workflow naming the alternatives to use next ('review it with preview_automation and enable it with set_automation_active after the user agrees') plus a clear exclusion ('Steps that call external services are not available here'). Both when-to-use-next and what-is-not-supported are stated.

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