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

Discloses behavior well beyond the annotations: atomicity, validation-before-persistence, config merge with null-clears-key semantics, edge replacement rules, and post-write split-node optimization. The one tension is that 'replace' discards the existing graph while destructiveHint=false, though the tool does not destroy the workflow itself, so this is a scoping nuance rather than a contradiction.

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?

Five tight sentences, front-loaded with the core action and mode split, then merge semantics, then safety and optimization notes. Every sentence carries distinct information; nothing is redundant.

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?

A mutation tool with a rich nested schema, an output schema, and annotations; the description covers mode behavior, merge semantics, validation, and the optional optimization pass. It lacks only preconditions (permissions, whether active workflows can be edited mid-run) which the description leaves to 'active-lead safety remains enforced by the workflow backend'.

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 33% schema description coverage, the description does the heavy lifting: it explains mode semantics, the graph-vs-patch relationship, per-node config merging (only sent keys change, null clears), and when patch.edges replaces the edge set. workspaceId is left to the schema, which already documents it thoroughly.

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 (patch or replace), resource (one workflow graph), and atomicity guarantee. This is clearly distinguished from the sibling campaignstack_edit_workflow, which edits the workflow itself rather than its graph structure.

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?

Gives precise operational guidance on choosing between the two modes: 'replace supplies the full non-anchor graph' vs 'patch starts from the current non-anchor graph'. It does not, however, state when to prefer one mode over the other or warn against calling this on an active workflow.

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