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

Annotations only declare readOnlyHint=false and destructiveHint=true; the description adds substantial context beyond that: partial-update semantics (omitted parts unchanged), concurrency refusal while open in browser, the archived-must-be-restored prerequisite, frozen revisions on open runs, and self-improvement updates surfacing in a report. This is rich behavioral disclosure an agent needs to call it safely.

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 core action and update model are front-loaded in the first sentence. The dense paragraph is long but each clause carries non-redundant meaning given the empty item schemas; a bulleted breakdown of node types and edge.data would improve scannability without cutting content.

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 complex graph-mutation tool with no output schema and empty item schemas, the description supplies the graph grammar, edge payload contract, valid topologies, and all write-precondition behavior. Nothing essential to invoking it correctly appears to be missing.

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% but the nodes/edges items are untyped empty objects, so the schema provides almost no structural meaning. The description compensates heavily by defining the node vocabulary (Start, Idea, Batch, Delivery, Workflow, Finish) and the required edge.data fields (instructionDocumentIds, contextKinds, optional ordered rulebookIds), plus the valid connection topologies.

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 opens with a specific verb+resource ("Edit one workflow") and immediately states the update model: nodes/edges replace the graph, name/description change details, omitted parts stay. An agent can distinguish this from get_workflow, delete_workflow, and archive_workflow without opening a 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?

It gives concrete when-to-use conditions (pass nodes+edges together to replace the graph; pass name/description to rename) and explicit when-not cases (refused while a vibe coder has it open, archived workflows must be restored first). It also sets exclusions ("do not create Instructions, Dictionary, or Features nodes or put text on lines"), though it never names a sibling tool as an alternative for those cases.

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