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

Annotations mark this tool as non-readonly, non-destructive, and open-world. The description goes beyond these by stating writes require workspace owner/admin, invoke performs a one-off run even when the MCP is not installed, and returns connect/checkout links for credential or payment needs. No contradiction with annotations is present.

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 lengthy but densely packed, organized around a clear workflow and distinct sections for invoke vs install, permissions, and the prompt library. Every sentence adds functional detail, and the front-loaded core flow helps readability. It is long but justified by the tool's breadth.

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?

The description covers the entire lifecycle: discovery, execution, installation, billing, permissions, and a separate prompt library. It even includes edge cases such as connect/checkout links and one-off invocation. However, it omits the 'resume' action and some parameters like immediate, leaving minor gaps for an otherwise thorough operational guide.

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 coverage, the description compensates by explaining the central 'action' parameter and its enumerated values, plus core args like tool_id, mcp_id, and arguments. However, many parameters (cancel_reason, immediate, tier_slug, conversation, prompt_vars) are not elaborated, leaving gaps for edge-case usage. It partially compensates but not fully for 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 opens with 'The official mcp.ai marketplace — the in-platform catalog of every MCP/tool, AND the way to run them,' clearly establishing the tool's dual role as catalog and execution layer. It then enumerates distinct actions (search, describe, invoke, install) and contrasts with sibling tools by its central marketplace function. This is a specific verb+resource description that distinguishes it from the narrower F360 and toolkit tools.

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 explicitly instructs when to use invoke over install: 'prefer invoke for a single/occasional use' and 'Use install only to make an MCP PERMANENT.' It also lays out the core flow search→describe→invoke, lists subscribe/cancel for billing, report_bug for feedback, and request_mcp when nothing fits. This gives the agent clear decision rules and alternatives.

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