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

Beyond the annotations, the description discloses key behaviors: invoke works even when the MCP is not installed, it returns a connect link when credentials are needed, a checkout/top-up link when wallet is empty with a retry instruction, and writes require workspace owner/admin. This is rich behavioral context that annotations (readOnlyHint: false, openWorldHint: true) do not provide.

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?

Although long, the description is densely packed and well-structured: it starts with the overall purpose, then the core flow, then key edge cases, then usage recommendations, and finally the prompt library. Every sentence adds distinct information, and the logical progression makes it easy to follow.

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 no output schema and high complexity (14 actions, 23 parameters), the description covers the primary search/describe/invoke flow, credential and payment handling, permission requirements, the distinction between invoke and install, and the prompt library. It gives an agent enough context to select and invoke actions correctly, including the prompt publishing link and billing actions.

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 description compensates for the 0% schema coverage by explaining core parameters: action values (search, describe, invoke, install, etc.), mcp_id, tool_id, arguments, prompt_vars, and prompt_slug. However, several parameters like limit, immediate, tier_slug, conversation, cancel_reason, and report_context are not described, leaving gaps for specialized actions.

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 identifies the tool as 'the official mcp.ai marketplace' and elaborates that it is both 'the in-platform catalog of every MCP/tool' and 'the way to run them.' It distinguishes itself from sibling tools by explaining the core flow (search → describe → invoke) and mentioning the prompt library, making its purpose and scope unmistakable.

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 when-to-use guidance: 'prefer invoke for a single/occasional use' and 'Use install only to make an MCP PERMANENT.' It also names alternatives like request_mcp for new builds, subscribe/cancel for billing, and search_prompts/get_prompt/publish_prompt for prompt text, giving clear directives on tool selection.

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