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

The description discloses significant behavioral traits beyond the annotations: writes require workspace owner/admin; invoke runs uninstalled MCPs without adding them to the toolkit; credential and payment failures return connect/checkout links and require a retry; search/describe expose installation status. This adds critical context about side effects, permissions, and failure modes that annotations alone do not convey.

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 well-structured, using explicit markers like 'Core flow:', 'KEY:', and 'Use install only...' to segment ideas. It is dense with necessary information for a complex tool and avoids redundancy. It could be slightly more scannable, but every sentence contributes to understanding.

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 (23 params, no output schema, no schema descriptions), the description covers the overall architecture, core flow, permission requirements, and edge cases (connect/checkout links). It explains what describe and get_prompt return. It stops short of detailing output formats, parameter syntax, or error handling, but provides enough for an agent to execute primary flows correctly.

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 thoroughly explains the 'action' parameter by narrating each action value (search, describe, install, invoke, etc.) within the flow. However, supporting parameters like query, limit, arguments, and the prompt_* fields are not explicitly mapped to actions, leaving the schema's bare names as the only reference. With 0% schema coverage, the description partially compensates but does not fully document all 23 parameters.

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 defines the tool as the official mcp.ai marketplace—the in-platform catalog and execution layer for MCPs/tools, plus a prompt library. It states a specific purpose with actionable verbs (search, describe, invoke) and distinguishes it from sibling tools by explaining its unique role, such as running uninstalled MCPs on a one-off basis.

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 usage guidance: 'prefer invoke for a single/occasional use' vs 'Use install only to make an MCP PERMANENT', contrasts with list_tools ('lists what is callable right now'), and explains when to use subscribe/cancel, report_bug, request_mcp, and the prompt library actions. This is exemplary when-to-use and when-not-to-use guidance, including precedence between alternatives.

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