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

Given the minimal annotations (readOnlyHint:false, destructiveHint:false), the description adds a useful behavioral trait: rejected fields are 'refused with reasons' rather than silently accepted — a meaningful expectation-setting disclosure. It does not reveal, however, whether updates are atomic or what happens to the draft after a successful update (e.g., revalidation), so it is below a 5.

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 description is two short sentences, front-loaded with the action and resource, with zero filler. The parenthetical field sample is efficient and illustrative, and the refusal clause earns its place as a high-value guardrail; a small deduction for not weaving in the alternative-tool routing that the schema has to supply separately.

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 with a large nested-object parameter and rich field semantics, the combination of the description's boundary statement and the 100%-covered schema is nearly sufficient. The main gap is the missing output-side info (no output schema exists and the description never hints what a successful call returns), plus no guidance on draft-state requirements (the title implies drafts only), but overall the agent can call it correctly.

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 100%; the schema already documents the partial-map semantics, the full accepted-field list, key-wise merge behavior, and the refused-field list, so the description's parenthetical field sample adds no new parameter meaning. This is the baseline 3 for high schema coverage — the schema does the heavy lifting.

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 states a specific verb and resource ('Update a draft's fields') with a concrete sample list of field categories (model, tools, system message, knowledge), which immediately signals what the tool operates on. It also draws a boundary against sibling tools by explicitly listing refused properties (status/workflow/organization/user), so an agent can distinguish it from build_agent, create_agent, attach_* and set_* tools without opening schemas.

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?

The description provides a clear when-not-to-use signal: status/workflow/organization/user fields are refused, so an agent knows not to route those updates here. However, it does not name the alternative tools (attach_*/set_* tools) in the description itself — that routing guidance lives in the schema's fields description, which is a minor gap against the rubric's explicit when/alternatives criterion.

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