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

Beyond the annotations (readOnlyHint=false, openWorldHint=true), the description reveals key behaviors: invoke runs uninstalled MCPs one-off, credential needs return a connect link, paid tools with empty wallet return a checkout link, and writes require workspace owner/admin. It also explains the installed_in_toolkit vs installed_in_workspace flags. No contradiction with 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 dense and long, but every sentence carries operational value, covering the many actions and edge cases. It front-loads the primary purpose and core flow. It could be improved with bullet points or section breaks, but the lack of fluff justifies a high score.

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 tool's complexity—14 actions, 23 params, no output schema—the description covers most core workflows: searching, describing, invoking, installing, listing, billing, reporting, requesting, and the prompt library. It also explains auth, payment, retry, and permission nuances. Missing details like how arguments are structured (JSON string) and the role of parameters like immediate or tier_slug prevent a perfect score.

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 must compensate and does add meaning for core parameters: action is mapped to the search/describe/invoke flow, tool_id identifies the specific tool, arguments are the params passed to invoke, and prompt_slug/prompt_vars relate to the prompt library. However, many parameters (limit, immediate, tier_slug, cancel_reason, conversation, etc.) are left unexplained, leaving gaps for a 23-parameter 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 description clearly states the tool is "the official mcp.ai marketplace — the in-platform catalog of every MCP/tool, AND the way to run them," and enumerates its core functions (search, describe, invoke, install, prompt library). This specific verb+resource framing distinguishes it from siblings like authenticate, connect, and toolkit_info.

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 an explicit core flow (search → describe → invoke) and gives practical guidance like "prefer invoke for a single/occasional use" and "Use install only to make an MCP PERMANENT." It also explains when invoke returns connect/checkout links and how to retry. It does not explicitly contrast with sibling tools such as connect or authenticate, but the hub nature is clear enough.

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