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

The annotations already declare destructiveHint=true, readOnlyHint=false and idempotentHint=false, so the bar is lower, and the description still adds substantial non-obvious behavior: the call is policy-gated by spend limit, unapproved payments are parked and re-executed on retry with the same idempotency_key, and the credential never reaches the agent. It omits failure/timeout behavior and what an unparked-but-denied call returns, and the openWorldHint=false annotation sits oddly against an explicit external api.stripe.com call.

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 tight sentences, front-loaded with the action and target before the gating flow and credential note, with virtually no filler. Minor redundancy: the inline '(POST, PUT, PATCH or DELETE)' duplicates the method enum already in the schema.

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 mutation tool with no output schema, the description supplies the critical control-flow facts an agent needs (gating, escalation, idempotent retry, credential isolation) while the schema covers most parameter detail. It would be stronger if it characterized the success/parked response shape or stated limits on path scope, but nothing essential to a correct invocation is missing.

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 86%, so the schema already documents path, body, facts, intent, method, user_token and idempotency_key in detail. The description restates the method set (already an enum) and the idempotency retry rule (already in the idempotency_key description), adding no new parameter meaning; the baseline of 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 names concrete operations (create, change, pay) against a concrete target (https://api.stripe.com) and enumerates the HTTP verbs used, so the agent knows this is a generic write proxy to the Stripe API. It falls short of 5 because it never names or contrasts with the obvious sibling stripe_demo_read, leaving the agent to infer the split from the title suffix.

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 explains the operational flow (spend-limit gating, ESCALATION_REQUIRED parking, retry with the same idempotency_key after approval), which is genuinely useful context for calling it. However, it gives no tool-selection guidance against siblings such as stripe_demo_read, pay, or card_link, nor any preconditions for choosing this tool over them.

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