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

Adds context beyond annotations by clarifying that the returned data is limited to safe metadata and explicitly enumerates sensitive fields that are excluded. This goes beyond the readOnlyHint, idempotentHint, and destructiveHint annotations, which already convey safety. The description does not mention pagination mechanics or authentication, but the core behavioral trait (what is and isn't returned) is well disclosed.

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?

Two sentences, zero fluff. The primary purpose and scope are front-loaded in the first sentence, and the important exclusion list is in the second. Every word earns its place, and it is appropriately concise for the tool's simplicity.

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?

The description is quite complete for a simple list tool: it states the operation, scope, and exclusions. With an output schema present, return details are covered there. The main gap is the lack of explicit pagination guidance (how to use cursor, when to fetch more pages), though 'bounded page' implies it. Given the tool's low complexity and the presence of an output schema, this is only slightly under-specified.

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?

The input schema has 50% description coverage: cursor has a description, but limit does not. The tool description adds no meaning for either parameter—'bounded page' hints at pagination but doesn't explain limit semantics or the relationship between cursor and limit. Since coverage is moderate and the description fails to compensate for the undocumented limit, this is a clear gap.

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 states a specific verb ('List'), a resource ('businesses'), and the scope ('bounded page of safe business metadata' for the InvoiceVista organization). It also explicitly lists what is omitted (addresses, contact details, payment settings, secrets), making it easy to distinguish from sibling tools like get_business or list_products. The purpose is unambiguous and differentiating.

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 description implies usage when a page of non-sensitive business metadata is needed, but it does not explicitly state when to use this tool versus alternatives like get_business or show_business_overview. No exclusions or alternate routing are provided. The guidance is implicit rather than explicit, so it only meets the 'implied usage' level.

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