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

Annotations already declare readOnlyHint: true, idempotentHint: true, and destructiveHint: false. The description adds substantial behavioral detail beyond those: it enumerates the return payload ('compatibility, per-model wiring, required inputs and final outputs, plus the node structure and connections') and explains the error-handling behavior for port mismatches ('comes back with the model's real port layout instead of a failed create'). No contradictions exist with the 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?

The description is three sentences, with the most critical information front-loaded: the purpose and non-destructive nature first, then the return values, then the specific usage context and mismatch behavior. Each sentence contributes substantive information, with no filler or redundancy.

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?

With no output schema, the description responsibly enumerates the return content and covers a key edge case (port-type mismatch behavior). Combined with the strong annotations and full schema coverage, the description provides enough context for an agent to understand what the tool does, when to invoke it, and what results to expect. No major gaps remain.

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%, and the schema itself provides rich explanations for nodes, connections, and include_optional, including decision guidance for optional inputs. The tool description adds only that the nodes/connections arguments are 'the same as create_flow', which is already mentioned in the schema. Since the schema does the heavy lifting, baseline 3 is appropriate.

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 description opens with 'Check whether a flow can be wired together, and see what create_flow would produce — without creating anything.' This uses a specific verb and resource while explicitly distinguishing preview_flow from create_flow by framing it as a dry-run validation tool. It is immediately clear that this is a non-destructive preview sibling to create_flow.

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?

The description gives clear context: it is for checking a hand-wired graph before creation, and it notes that nodes/connections arguments are shared with create_flow, so a port-type mismatch returns the model's real port layout instead of a failed create. However, it does not explicitly state when not to use it or compare it to other siblings like find_compatible_models, so it stops short of full when/when-not guidance.

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