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

Adds real behavioral context beyond the annotations: the edit is atomic — "If an edit or the resulting flow has problems, nothing is saved and the problems are returned" — which tells the agent failures are non-partial and surfaced as a problem list. The annotations already flag destructiveHint, so the remaining gap is only around what else gets touched (e.g. whether prior flow state is replaced).

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 short sentences: purpose first, target selection second, failure behavior last. Every sentence carries information an agent needs and nothing is repeated from the schema.

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-parameter tool with a nested oneOf edit vocabulary, no output schema, and destructive semantics, the atomicity note is good but there is no pointer to get_flow_guide/get_blocks for discovering block types and refs, and no hint about what the returned problem list looks like — gaps an agent will hit on first call.

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 only 50%, and the description compensates by declaring the target selector as a one-of across command_id/event_listener_id/message_id, a constraint the schema does not encode. It still says nothing about edits op semantics or flow_source_id, so the compensation is partial.

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 (edits/saves) and resource (the flow), and enumerates the three target kinds: command, event listener, message component. That distinguishes it well from the create_*/delete_* siblings, though it never names a sibling (e.g. get_flow_guide or create_command) to anchor the distinction.

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?

"Pass one of command_id, event_listener_id or message_id" tells the agent how to select a target, which is genuine usage guidance, but there is no statement of when to use this versus create_command/update_message, nor any prerequisite such as needing a flow guide or existing flow.

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