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

Annotations declare destructiveHint=true and readOnlyHint=false, and the description adds the crucial detail of which action is destructive (disconnect deletes the stored key) plus the security-relevant fact that keys are never shown back. It does not mention the `confirm` parameter or any guard/prompt before the destructive disconnect, which leaves the mutation path slightly under-specified.

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 one-line summary is front-loaded and the per-action breakdown follows in compact order. Every sentence carries distinct information — no restatement of the title or 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?

An output schema exists, so return values need no explanation, and the action taxonomy is fully covered. The remaining gap is the undocumented `confirm` parameter and the absence of an explicit statement that disconnect requires confirmation.

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%, so the description carries the burden. It compensates well for `action`, documenting all four enum-like values and their behavior, and implies `account` scoping, but the `confirm` boolean (default false) is never mentioned despite being relevant to the destructive disconnect path.

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 specific verbs (lists, re-checks, disconnects, re-defaults) against a specific resource (connected ChatGPT Ads accounts), then enumerates each action's effect. An agent can distinguish this account-management tool from sibling list_* and connect_* tools without opening the schema.

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 usage: `check` is prescribed for the authorization-error case, with the reasoning that a revoked key looks like a missing permission. `set_default` explains its downstream effect on other ChatGPT Ads tools, and each action is defined by when it applies. This is close to a complete decision table.

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