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

The annotations include readOnlyHint: false, idempotentHint: false, and destructiveHint: false. The description goes beyond these limited annotations to specify that invoke runs tools 'pontualmente' without installing, that auth/connect links are returned, and that billing/top-up links are provided whenwallet is empty. It also mentions permission requirements for writes, adding valuable behavioral context not covered by 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 description is a single dense paragraph covering many topics. It includes essential information, but its length (over 200 words) and lack of structure (no bullet points or separate sections for actions) makes it harder to scan. Each sentence does add value, but the format could be improved with better organization, so a 3 is appropriate.

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?

Given the high complexity (23 parameters, multiple actions, billing, auth, prompt library) and minimal annotations (no output schema, low schema coverage), the description is quite thorough. It explains the overall flow, distinguishes between search/describe/invoke, mentions permission requirements, and covers additional features like prompt library and subscriptions. It's not perfect but provides a solid understanding of the tool's full scope.

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 0%, and the description does NOT define each parameter individually.Defaulting to 3 is reasonable because the description explains the action enum values (search, describe, install, etc.) and connects them to the core flow. However, it does not clarify other parameters like 'immediate', 'conversation', or 'cancel_reason' beyond what the schema shows. Since there are 23 parameters, the description could do more to explain how arguments and prompt_vars are used, so no higher than a 3.

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 clearly states the main purpose: to access the mcp.ai marketplace, discover MCPs, and run them. It enumerates the core actions (search, describe, invoke) and explains the overall value. It also distinguishes itself from siblings like connect and authenticate by covering the marketplace functionality broadly.

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 provides explicit usage guidance: when to use 'invoke' vs 'install', preferring invoke for one-off use and install for permanent additions. It also clarifies that writes require owner/admin permissions, and when to use 'report_bug', 'request_mcp', etc. This is among the most detailed usage guidance I've seen.

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