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

Annotations only mark the operation as not read-only, not destructive, and not idempotent. The description adds meaningful behavior: the graph is replaced entirely (not merged), and a graph update returns a warnings array with create_flow-like checks. It does not mention response shape for non-graph updates or failure modes, but the disclosed replacement and warning behavior goes beyond 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 focused sentences. The first sentence states the operation and scope, the second clarifies partial-update semantics, and the third delivers the most critical graph-related warning. No filler or repetition of schema details.

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?

Given the nested graph object, 5 parameters, and no output schema, the description is largely sufficient. It covers what changes, how partial updates work, and what to do with warnings when updating the graph. It does not describe the standard success response for non-graph updates, but this is a minor gap given all the key invocation semantics are present.

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%, so the baseline is 3. The description adds value by clarifying that only provided fields are changed and that supplying a graph means providing ALL nodes/edges because it replaces the entire graph. It also explains the conditional warnings response when graph is supplied, which is not obvious from the schema alone.

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 states a specific verb ('Update') and resource ('a flow'), and enumerates exactly which fields can be changed: name, description, graph, or enabled state. It also clarifies the partial-update semantics ('Only provided fields are changed'), which distinguishes it from create_flow and other flow mutations.

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 updating an existing flow, and the graph parameter has special replace-entire-graph semantics. It references create_flow's checks, providing a useful link, but does not explicitly say 'use create_flow for new flows' or 'use toggle_flow for a simple enable/disable toggle.'

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