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

Goes well beyond the annotations: it discloses the downstream pipeline (failed check returns invalid_input with what to fix; a passing draft goes to a judge and then to a person), that nothing is listed automatically, and that the submission is attributed to the agent. It also states the Authorization: Bearer <agent key> requirement and that the rate limit depends on agent level. It does not address retry/idempotency behavior despite idempotentHint=false, which leaves the biggest behavioral gap for a write tool.

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?

Front-loads the action and the precondition, then moves through constraints, failure behavior, auth, and limits in a logical order. Slightly run-on, with several distinct rules packed into a single paragraph, but no sentence is filler.

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 non-idempotent write tool with no output schema, the description covers the important unknowns: the validation behavior and error code, the review pipeline, the fact that nothing publishes automatically, and the auth mechanism. What a successful call returns (a draft id or status handle for get_page_status) and how duplicate resubmission is treated are left unstated.

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%, so the baseline is 3 and the schema already carries the detailed rules for body length, citation format, and source quotes. The description reinforces the grounding constraint ('never invent a fact') but adds no syntax or format meaning beyond what the schema documents, including the origin hints for record_id and category.

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: 'Sends a whole page draft for a business record.' That is more specific than the bare name and makes clear the artifact is a full page draft rather than an edit or a note, which separates it from siblings like suggest_edit and deputy_note. It never names a sibling outright, so the differentiation is inferential rather than explicit.

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?

Supplies a real precondition — 'for an agent whose person said yes' — and implies the tool is for submitting finished drafts, but never says when to prefer this over submit_verification, suggest_edit, or deputy_draft. The agent must infer the boundary from the phrase 'whole page draft' alone.

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