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

With no annotations present, the description carries the full burden and does so well: it discloses the two return shapes (approve_url vs pending_approval), the out-of-band owner email/approval side effect, and the privacy guarantee that Plinth never sees card numbers. That is substantive behavioral context an agent could not infer from the empty schema.

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-loaded with the action, then the success path, then the async path. Every clause earns its place — no restating the name, no filler — and the escalation to 'poll approval.status' lands last where the agent needs it.

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, so the description must explain returns; it covers both response cases and the required next step for each. For a 0-param, annotation-less tool this is complete enough to call correctly without opening anything else.

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?

There are zero parameters, so the baseline is 4. The description instead spends its words on return semantics (approve_url, pending_approval) and the approval flow, which is the right place for value given a 0-param tool.

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 action and resource: ask the owner to add or replace the payment card. The name 'billing.card' alone is ambiguous (could read as a read op), but the description immediately disambiguates it as an owner-approved write flow. It does not explicitly name siblings like billing.status or approval.status as points of contrast, so it stops short of a 5.

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?

Gives clear operational context: approving opens a Stripe page, and if pending_approval is returned the agent should tell the owner it is waiting and then poll approval.status. This is actionable post-invocation guidance with a named follow-up tool, though it doesn't state exclusions or when to prefer an alternative (e.g. billing.status) before calling.

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