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

Beyond the annotations (which already say non-destructive, idempotent, closed-world), the description discloses a validation rule that will cause rejection (a step consuming output from a later step) and the versioning/undo consequence (undo.version_id restores the prior arrangement). Those are exactly the behavioral facts an agent needs and cannot get from the annotation flags.

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 action, then the exclusion, then the failure mode, then the undo path — every sentence carries information. The final clause 'undo.version_id puts it back' is dense to the point of being slightly cryptic about where that field comes from.

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?

With no output schema, the description usefully volunteers the undo.version_id return value, and it covers the key rejection case for a mutation tool. It stops short of stating prerequisites such as whether the workflow must be in a draft state, who may move steps, or what happens to in-flight runs.

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 only 33%, so the description has to carry weight: it does explain that placement means 'before or after another step', effectively documenting the nested placement.kind enum and placement.step_id. However, workflow_id is undocumented in both schema and description, and step_id's role is only implied, leaving a gap at the low coverage level.

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 names a specific verb (move) and resource (a workflow step) plus the placement model (before/after another step), which is unambiguous. It also carves out scope (no conditions or loops) and points to the dashboard for those cases, though it never names a sibling tool as the alternative path.

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?

It clearly states when this tool does NOT apply — workflows with conditions or loops are rearranged on the dashboard — which is real routing guidance. It does not reference edit_step or add_step for other kinds of step restructuring, so the alternative-tool picture is incomplete but the primary exclusion is explicit.

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