update_flow

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

Goes well beyond the annotations, which only say the call is not read-only, not idempotent, and not destructive. The description discloses the key non-obvious behaviors: a new definition lands as DRAFT rather than live, it is validated like on create, the running version is unaffected until publish, and node positions are discarded on definition change.

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 tight sentences, front-loaded with the core action and capabilities, followed by the side-effect warnings. No filler or restatement of the name.

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 nested, non-idempotent mutation tool this covers the critical mental model: draft-versus-live, validation parity with create, and layout reset. The main residual gap is whether omitted fields are preserved, plus no mention of auth or rate limits, though the safety profile is partly carried by annotations.

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?

With only 40% schema description coverage and a deep nested definition object, the description compensates by tying each optional parameter to an outcome (rename, retarget, tag, replace) and by explaining what happens to the definition payload. It stops short of clarifying null/omission semantics for tag_id or how partial updates treat untouched fields.

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+resource ('Update a flow') and enumerates the four updatable facets (rename, retarget channels, set tag, replace definition), which map directly onto the optional schema properties. An agent can distinguish this from create_flow, publish_flow, or validate_flow without opening the schema.

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?

Usage is implied by the draft/publish narrative ('the live version keeps running until you publish'), which hints that publishing is a separate step via publish_flow, but no sibling is named and there is no explicit when-not guidance. An agent must infer the workflow ordering rather than being told it.

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