Apply bulk settings changes

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

Annotations already declare destructive=true, idempotent=true, openWorld=false, but the description adds substantial context: per-account transactions, three-way per-row outcome (ok/unchanged/failed with reason), a 24-hour revert window via batch_id, and the fact that sensitive-field confirmation may block on owner approval. It doesn't describe rate limits or what happens to rows beyond 100, keeping it short of 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?

One dense paragraph that front-loads the write semantics, result shape and revert path before the constraints. Every sentence carries information, though the trailing 繁中 restatement duplicates content already given in English.

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?

With no output schema, the description carries the return contract itself (per-row ok/unchanged/failed plus reason, and batch_id), and it covers the transactional guarantee, the idempotency contract and the preview gate. An agent has everything needed to invoke this destructive bulk write 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 coverage is 100%, so the baseline is 3; the description still adds meaning by stressing that idempotency_key is required and that a retried request with the same key returns the first result, and that a preview_id not matching the changes is refused. confirm_sensitive gains the consequence that confirmation may wait for owner approval, which the schema does not say.

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+resource+scope: writes a batch of settings changes to up to 100 accounts, each in its own transaction, returning per-row results and a batch_id. It is clearly distinguished from preview_account_settings (must be called first), update_account_settings (single-account sibling) and revert_account_settings_batch (the undo path).

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?

Explicit ordering rule: nothing is written without a preview, preview_id from preview_account_settings is required from Claude/ChatGPT connections, and the tool applies only after the user has seen and confirmed the preview. It also names the undo alternative (revert_account_settings_batch within 24h) and the case that requires confirm_sensitive:true.

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