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

The description discloses several non-obvious behaviors not inferable from annotations: invoke runs a one-off install (even when the MCP is not installed), returns connect links for credentials and checkout links for payment, and requires workspace owner/admin for writes. It also explains the difference between installed_in_toolkit vs installed_in_workspace flags, adding rich context beyond 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 description is a single dense paragraph but every sentence carries unique information. It is not front-loaded or bulleted, which could be improved, but it avoids fluff and uses clear, imperative language. The length is justified by the tool's complexity, though structure could be enhanced with line breaks.

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?

For a tool with 23 parameters and no output schema, the description covers the primary workflows (search/discover, describe/select, invoke/run), permission requirements, error flows (auth/checkout links), and the separate prompt library feature. It omits the 'uninstall' and 'resume' action details and some parameter-specific behaviors, but these are minor for an agent selecting the right action.

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 0% schema description coverage and 23 parameters, the description is the primary source of semantics. It explains the `action` enum values in prose (search, describe, install, invoke, list_tools, subscribe, cancel, report_bug, request_mcp, search_prompts, get_prompt, publish_prompt) and mentions prompt_vars by example. However, many parameters (e.g., limit, immediate, tier_slug, cancel_reason, conversation) receive no explanation, leaving gaps.

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 begins with 'The official mcp.ai marketplace — the in-platform catalog of every MCP/tool, AND the way to run them,' clearly stating its purpose. It details the core flow (search→describe→invoke) and distinguishes itself from sibling tools by describing its role as the central dispatcher and catalog.

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 gives explicit guidance on when to use which action: 'Use install only to make an MCP PERMANENT...; prefer invoke for a single/occasional use.' It also contrasts list_tools, subscribe/cancel, report_bug, and request_mcp, and explains when to use the prompt library functions. This level of contextual direction goes beyond vague suggestions.

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