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

Annotations already declare non-read-only, idempotent, non-destructive behavior, so the description rightly doesn't restate that. What it does add is genuinely new and useful: the builder:read vs builder:write scope requirement per action class. It omits other behavior an agent would want — that drafts are private/isolated, whether save_draft mutations are revision-checked, and how jobs (jobId actions) behave — so it is helpful but incomplete.

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?

Two front-loaded sentences with no filler; purpose first, auth constraint second. The terseness is efficient, though part of the brevity is under-specification rather than discipline.

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 tool this complex — 18 actions, a deeply nested draft model, job polling actions — the description is far too thin. An output schema covers return values and annotations cover safety, but an agent still cannot tell which action to call first, what the draft workflow is, or how idempotencyKey interacts with the declared idempotent behavior.

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 0% while the command parameter is a large discriminated union of roughly 18 actions, many with nested payloads (draft, input, files, operations). The description says nothing about the command dispatch shape, any action name, or what idempotencyKey is for. The action const names are partly self-explanatory, which keeps this from a 1, but the description contributes essentially zero parameter meaning.

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 — authoring and testing private revisioned agent drafts — which is recognizable against siblings like publish and run. It doesn't explicitly contrast with manage or run, so the differentiation is implied rather than stated.

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?

There is no guidance on when to reach for this tool versus publish, manage, or run, and no mention of the draft lifecycle (start -> save -> validate -> test -> export) that the 18-action command union clearly implies. The only usage-adjacent signal is the read-vs-write permission split, which is about credentials, not tool selection.

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