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

Goes well beyond the annotations by disclosing a hard authorization constraint (refused regardless of role) and the semantic effect on downstream state: the vendor's bills count as approved ahead of time from one account, or stop being so. This is exactly the kind of context annotations cannot convey.

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 purpose is front-loaded, but the human-only point is repeated three ways (the 'HUMAN-ONLY' line, 'Ask your human to do it', and 'A person sets autopay in the app, whatever an agent's role'), and 'Effects:' restates the opening sentence. Emphasis is justified here, but the text is longer than needed.

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?

No output schema exists, yet the description covers what changes in the system and why an agent must not call it. What remains uncovered (e.g. what the refusal looks like, whether an existing autopay must be off before setting a new one) is minor for a tool agents are told not to invoke.

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% and each parameter is documented in-schema, so the baseline is 3. The description only restates the account/off relationship conceptually ('put on autopay from one account, or take them off') without adding format or constraint detail.

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?

First sentence states a specific verb and resource: put a vendor's bills on autopay from one account, or take them off. It is distinguishable from siblings like purch_declare_bill_series and purch_record_bill_payment by describing the standing-approval effect.

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 says the act is refused to agents whatever their role and instructs the agent to ask its human to perform it. It also names the agent's legitimate alternatives (recording bills and payments) so the agent knows what it should do instead.

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