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

Annotations already declare readOnlyHint=true, openWorldHint=true and destructiveHint=false, so 'Read-only' in the description largely restates structured data. The description does convey genuine openness — an unbounded set of endpoints across the whole account — but says nothing about pagination, rate limits, auth/scopes, or how request failures surface.

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?

A single front-loaded sentence that leads with the capability and then enumerates examples; there's no filler. The trailing 'Read-only' is mild redundancy against the annotations, keeping it just shy of a 5.

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?

With only two parameters, full schema coverage and annotations covering safety, the essentials are present, and no output schema means return values needn't be explained. Still, for an open-world dispatcher the critical workflow — search for the operation id, inspect it with stripe_api_details, then call — is only half-visible, appearing in the schema rather than the description.

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 the baseline of 3 applies; the schema itself explains that path parameters go keyed by brace names and that array fields must be JSON arrays. The description adds no further parameter semantics beyond the resource examples that hint at what operation ids exist.

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 (read) and a clear scope: any Stripe GET operation, with concrete resource examples (customers, charges, invoices, subscriptions, payouts, disputes, balance). The word 'GET' plus 'Read-only' cleanly separates it from stripe_api_write, though it never names that sibling or the higher-level summary tools explicitly.

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?

Usage is implied by 'read anything ... with any Stripe GET operation', and the read-versus-write split is clear enough to avoid stripe_api_write. However, it gives no guidance on when to prefer the purpose-built siblings (stripe_mrr_summary, stripe_failed_payments, stripe_churn_summary, stripe_account_info) over this generic dispatcher, and no mention that stripe_api_search must be used first to obtain the operation id.

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