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

With no annotations, the description carries the full burden and does well: it discloses that the artifact is a hosted Stripe page, that payment is performed by a human rather than the agent, and that MM takes custody of funds ('MM holds the money once it arrives'). Undisclosed behavior remains — whether the link expires, whether calling again mints a new link, and what deal states permit it — which keeps this below 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?

Three short sentences, front-loaded with the deal-type condition and the human-handoff rule, with no filler. The trailing custody sentence ('MM holds the money once it arrives') is marginally tangential but does carry behavioral value.

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 three-required-parameter, no-output-schema tool, the description covers what the link is and who should use it, but leaves lifecycle questions unresolved (expiry, regeneration on repeat calls, prerequisites such as the deal being in a fundable state). An agent can call it, but not predict what happens on a second call or an expired link.

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 all three parameters (email, token, deal_id) are already documented with examples in the schema. The description adds no parameter meaning at all — notably it doesn't say whether the email must match the deal's buyer or how token is scoped — so the baseline 3 applies.

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?

The description states the resource concretely — 'a Stripe page where the buyer pays by card, ACH bank debit or wire' — and the leading qualifier 'For card / bank deals' implicitly separates it from the USDC-link sibling. The verb ('get/retrieve the link') is left implicit and only recoverable from the tool name, so it falls short of a clean verb+resource statement.

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?

It gives an explicit usage condition ('For card / bank deals') and an explicit handling instruction ('Open it in a browser… agents should hand it to their human'), which is exactly the routing decision an agent needs. It never names the alternative tool for non-card/bank deals, so the exclusion is implied rather than stated.

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