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

Adds substantial context beyond the annotations: spend-limit gating on every call, silent parking of unapproved payments for owner approval with a defined retry protocol, and the guarantee that the credential never reaches the agent. That is exactly the behavioral disclosure a destructive, non-idempotent mutation proxy needs.

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 sentences, front-loaded with the verb/resource statement, followed by the escalation rule and the credential guarantee; nothing is padding. The middle sentence is dense but every clause carries operational weight.

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 7-parameter open-ended proxy with no output schema, the description covers the key unknowns: gating, escalation/retry, and credential handling. It stops short of describing what a call returns or how ESCALATION_REQUIRED is surfaced to the agent, which would close the last gap.

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 coverage is 86%, so the schema already documents path, body, facts, intent, user_token, and idempotency_key; the baseline applies. The description's idempotency_key retry guidance largely repeats what the schema field already says, and it adds no meaning for `facts` or `intent`, which are the policy-relevant parameters.

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 verb set (create/change/pay) and resource (https://api.stripe.com) with the allowed HTTP methods, which cleanly separates it from the *_read siblings. It does not, however, distinguish itself from other write-path siblings such as pay or stripe_demo, leaving that routing to the agent.

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?

The throttle/escalation flow is described (parked for owner, ESCALATION_REQUIRED, retry with same idempotency_key), which is real usage context. But the description never names an alternative tool or states when *not* to use this raw proxy (e.g. when `pay` or a purpose-built tool is preferable), so usage selection is only implied.

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