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

Annotations already flag destructiveHint=true and idempotentHint=false, but the description adds genuinely new behavior: the new definition is saved as a DRAFT, validated the same way as on create, and the live version keeps running until publish. It also discloses a side effect an agent could not infer from schema or annotations — node positions are dropped and the builder re-lays out the graph.

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 sentences, front-loaded with the action and its options, then the draft/publish lifecycle, then the side effect. Every clause carries information; the parenthetical about re-layout is the kind of detail that prevents a wrong assumption.

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?

There is no output schema, so the description should carry the lifecycle story — and it does, covering draft creation, validation parity with create, and live-version persistence. It omits what a validation failure looks like and does not spell out that omitted fields are left untouched (only implied by "and/or"), which is the main remaining gap for a nested, destructive mutation.

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?

At 40% schema coverage and heavy nesting, the description carries real weight: it maps the mutable fields to the schema properties and explains the semantics of `definition` (draft-saved, create-equivalent validation, positions discarded). It does not clarify `id` beyond the schema, nor the null behavior of `tag_id` or the channel enum, leaving some coverage gaps.

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?

"Update a flow" names a specific verb and resource, and the follow-up sentence enumerates exactly which attributes are mutable (name, channels, tag, definition). An agent can distinguish this from create_flow, publish_flow, or discard_flow_draft by the field list. It stops short of naming a sibling explicitly, so it earns a 4 rather than a 5.

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?

"and/or" signals partial updates, and "the live version keeps running until you publish" implicitly routes the agent to publish_flow for go-live. That is clear contextual guidance but not an explicit when/when-not statement naming the alternative tool, so it is not a full 5.

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