stripe_get_invoice

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

Annotations already declare readOnlyHint=true, idempotentHint=true, openWorldHint=true, and destructiveHint=false, so the safety profile is carried by structured data. The description adds genuine context beyond that: the exact-authority routing restriction, the fact that effect is required, must be 'read', and is verified by Spring, plus a clarifying note that approval_ref only applies when resuming a write. No contradiction with 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?

The Args list format is clean and each parameter line is a compact label, making the description easy to scan. However, the opening sentence is pure redundancy, restating the tool name twice in one line, and the saved space is not redirected toward more valuable content like an arguments example or usage hint.

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?

Despite the output schema covering return values, the description leaves a significant operational hole: how to construct the arguments payload to fetch a specific invoice (e.g., invoice ID, field names, JSON format). With 0% schema coverage, an agent understands the platform envelope parameters but cannot determine how to actually request an invoice, making correct invocation dependent on outside knowledge.

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?

With schema description coverage at 0%, the description is the sole source of parameter meaning, and it does add semantic labels for all seven parameters (e.g., project_ref as 'exact project correlation reference', idempotency_key as 'stable business-action identity', connector_account_ref as 'project-bound connector account alias'). However, the critical arguments field is left as a vague 'JSON string of arguments for the connector operation' with no indication of what a get_invoice call requires — such as an invoice identifier — which is the one parameter an agent must actually construct to use the tool.

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 only purpose statement — 'Stripe connector operation `get_invoice` (platform tool `stripe.get_invoice`)' — restates the tool name rather than describing what it does. It never explains that this fetches a specific Stripe invoice's data, nor does it differentiate from siblings like stripe_list_invoices, stripe_create_invoice, xero_get_invoice, or quickbooks_get_invoice. The verb and resource are only recoverable from the name itself, which makes this effectively a tautology.

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?

No when-to-use guidance is given relative to alternatives such as stripe_list_invoices (for enumerating invoices) or stripe_raw_api_request (for custom calls). The routing note ('Routes only through the exact project/account governed connector authority') is a constraint on how the call executes, not a directive on when to select this tool. There are no explicit use cases, exclusions, or alternative references anywhere in the description.

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