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

Beyond the annotations (readOnlyHint false, destructiveHint false), the description discloses permission requirements for writes, the one-off execution behavior of invoke, connect/checkout link fallbacks with retry instructions, and the distinction between installed_in_toolkit vs installed_in_workspace. This is rich, non-obvious behavioral context.

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 information-dense, covering a complex multi-action tool without filler. It front-loads the core flow and highlights critical caveats. A bulleted structure could improve scannability, but every sentence earns its place.

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 params, no output schema), the description covers the most important operational aspects: search/describe/invoke flow, install vs invoke semantics, auth/payment fallbacks, permissions, and the prompt library. It leaves some actions like resume and several params unexplained, but overall provides a strong operating manual for an agent.

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 coverage is 0% with 23 parameters, and the description compensates by explaining the meaning of key actions and a few parameters (action, mcp_id, tool_id, arguments, prompt_vars implicitly). However, many parameters like immediate, tier_slug, conversation, report_context, prompt_title, and cancel_reason remain undocumented, leaving the agent to infer their purpose from the action context.

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 with a distinct dual role: cataloging MCPs and executing them. It names explicit actions like search, describe, invoke, install, and the prompt library, making it easy to distinguish from sibling tools like authenticate or connect.

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 a core flow (search → describe → invoke), explicitly contrasts invoke vs install, states when to use request_mcp for gaps, and explains subscribe/cancel/report_bug. It tells the agent when to prefer invoke for one-off use and install for permanent toolkit membership.

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