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

Given annotations only provide high-level hints (readOnlyHint=false, etc.), the description carries the full burden and does so thoroughly. It explains that invoke runs one-off without installation, returns connect/checkout links when credentials or payment are needed, requires owner/admin for writes, and clarifies the difference between installed_in_toolkit and installed_in_workspace. 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 long, but the tool is exceptionally complex with 23 parameters and 14 actions. It is front-loaded with the primary purpose, then organized into sub-contexts (core flow, invoke vs install, permissions, prompt library). While it could benefit from bullet points, every sentence contributes meaningful information without redundancy.

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 of this complexity, the description is remarkably complete. It explains the end-to-end flow, edge cases (auth and payment requirements), the distinction between invoke and install, permission requirements, and the secondary prompt library feature. It also describes the return behavior of key actions (invoke returns links, get_prompt returns text). No output schema exists, so the description's coverage is sufficient.

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 provides semantic context for the crucial `action` parameter and the core flow (e.g., tool_id, arguments, prompt_vars), and mentions several prompt-related params. However, with 23 parameters and 0% schema description coverage, many parameters (immediate, tier_slug, cancel_reason, cancel_comment, request_name, etc.) are left unexplained, leaving the agent to guess their meaning from names alone.

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 catalog, with a specific primary function of discovering and running MCPs. It details a concrete workflow (search → describe → invoke) and distinguishes itself from sibling tools by defining its role as the central hub for all MCP and prompt management.

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 offers explicit usage guidance: 'prefer invoke for a single/occasional use' and 'use install only to make an MCP PERMANENT'. It also contrasts list_tools as reporting what is callable right now, and distinguishes prompt-related actions. It additionally specifies prerequisite permissions for writes (workspace owner/admin), making when-to-use clear.

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