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

Annotations already declare readOnlyHint=false, destructiveHint=false and idempotentHint=true, so the description's job is to add nuance, which it does: it discloses the referential-integrity block on removing in-use inputs and the staging behavior where deployed workflows keep running the old version until deploy_workflow. It does not say whether partial failures roll back or whether the whole update is atomic.

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?

Four short sentences, front-loaded with the mutation scope, then constraints, then the deployment caveat. No restatement of the title and no filler; each sentence carries a distinct rule.

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 six-parameter mutation tool with no output schema, it covers scope, a hard removal constraint, and the deployment consequence of the change. The remaining gaps — return shape and atomicity/validation behavior — are minor given annotations mark it idempotent and non-destructive.

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 description coverage is only 33%, so the description must carry weight; it does map its prose onto the six parameters by naming rename (name), description, and the add/remove/update input operations with their sub-fields (label, required flag, example value). However, it adds no detail on the text/array input `type` enum, on name-collision behavior when adding an input that already exists, or on whether add/remove/update can be combined in one call.

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 concrete verbs and the exact scope of the resource: rename, change description, and add/remove/change start inputs. It explicitly excludes steps ("Steps are not changed here"), which separates it from the step-editing siblings without requiring the reader to open any 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 a clear negative rule (steps are not changed here) and names the follow-up tool by stating a deployed workflow keeps its deployed version "until deploy_workflow." It also states a precondition for removal (an input a step still uses cannot be removed). It stops short of explicitly routing to edit_step/add_step by name, so guidance is strong but not fully exhaustive.

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