update_flow

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

Beyond the annotations (readOnlyHint=false, idempotentHint=true), the description discloses critical behavioral risks: writing action-instance rows over REST does not recompile the flow, leading to desync/corruption. This adds significant context that annotations cannot convey, making the tool's safety profile very transparent.

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: purpose, the critical warning, and the guidance to edit steps in the UI. Every sentence carries essential information with no fluff, and the purpose is front-loaded.

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 metadata update tool with full schema coverage and no output schema, the description is complete: it explains the scope, the caveat about step editing, the write nature, and the underlying reason (compiled snapshot). The annotations cover idempotency and non-destructive behavior, so no critical 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 coverage is 100%, with each parameter having a basic description (e.g., 'New name', 'Activate (true) or deactivate (false)'). The description reinforces that these are metadata fields (activate/deactivate, name, description, run-as) but does not add deeper semantic detail beyond the schema. This matches the baseline for full schema coverage.

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 clearly states the tool updates flow or subflow METADATA only, listing specific fields (activate/deactivate, name, description, run-as). It distinguishes itself from step editing and clearly scopes the operation to metadata, which differentiates it from create_flow and get_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 explicitly states when NOT to use this tool for editing steps, and provides the alternative: 'Edit steps in the Flow Designer UI.' It also makes clear that it is for metadata updates only, giving unambiguous usage context.

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