Post EInstances Tos

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

Annotations only give generic hints (readOnly=false, idempotent=false, openWorld=true, destructive=false); the description goes well beyond them by disclosing the out-of-band human action, the post-acceptance redirect with tos_id as a query parameter, the tos.accept webhook, and the non-reusability of idempotency_key. These are exactly the behavioral traits an agent cannot infer from structured fields, and nothing contradicts the annotations.

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 core behavior in the first sentence, then workflow, then parameter notes. Four sentences, each carrying distinct operational information with no repetition of the title or name.

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?

There is no output schema, and the description compensates by explaining that the return value is a URL and what happens after acceptance. What keeps it from a 5 is the silent customer_id parameter, which is relevant to a ToS acceptance flow and is left unexplained.

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 must compensate. It explains redirect_url (browser destination, receives tos_id as a query parameter) and idempotency_key (any unique string, cannot be reused), which is genuinely additive — but customer_id and instance_id are never mentioned, leaving half the inputs without any prose meaning.

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?

A specific verb and resource: it returns a hosted URL where an end customer accepts BlindPay's terms of service. No sibling tool covers terms of service, so there is nothing to disambiguate against, which is why this lands at 4 rather than 5 — but an agent immediately knows what it produces.

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 states when this tool is the right call ('a person must open it in a browser and accept; it cannot be accepted through the API') and chains the output into the next step ('Pass that tos_id to Create Customer'). It also names the redirect_url prerequisite, so the agent knows the full workflow rather than just the invocation.

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