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

Annotations already flag this as destructive and idempotent, and the description builds on that with concrete operational detail: in-use options (including archived tasks) cannot be removed, used status categories cannot change, visibility/team membership are untouched, requestId must be reused on retry, and permissions are enforced at workspace/project/account levels.

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?

Purpose and the changes-vs-workflow fork are front-loaded, and nearly every sentence adds operative information (IDs, removal constraints, retry semantics). It is a dense block with long compound sentences, and the trailing "Item updates require..." line reads as context bleed rather than this tool's contract.

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 5-parameter mutation with nested objects and no output schema, the description covers the mutation semantics, constraints, auth, and even the return shape ("the result returns the workflow with its IDs"). It does not describe failure behavior on version mismatch or conflict, which for a destructive versioned write is a notable omission.

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 40%, so the description must carry weight, and it delivers: it explains that a missing `id` is derived from the name (e.g. apply-next), that `version` must come from get_workspace, and that `requestId` must be unique per action and reused on retry. The stray sentence about item updates needing versions from get_tasks/get_items slightly muddies the version semantics for this tool.

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 and resource — "Change an authorized project's workflow" — and enumerates the affected domains (statuses, labels, sections, task defaults). No sibling tool performs this operation, and an agent can identify the target object and action immediately.

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?

Explicitly routes between the two operating modes: send `changes` for targeted edits that leave everything else intact, or send the complete `workflow` to replace it. It also states the prerequisite (current version from get_workspace) and the authorization level (workflows:write, workspace owner/admin).

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