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

The description discloses key behaviors beyond annotations: it explains that invoke works even if the MCP is not installed, that it runs tool one-off without bloat, and that writes require workspace owner/admin. It also details connect links for auth and checkout links for payment, plus the prompt library's shareable links. These are critical operational details not covered by the minimal annotations (readOnlyHint=false, openWorldHint=true, etc.), and there is no contradiction.

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 packed with essential information. It follows a logical structure: first the marketplace overview, then the core flow, then key distinctions (invoke vs install), then auxiliary actions, and finally the prompt library. While a wall of text, it is efficient and each sentence contributes to understanding. Minor improvement could be breaking into sections, but it remains appropriately concise given the tool's complexity.

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 broad scope (14 actions, many with prerequisites and side effects), the description is remarkably complete. It covers the entire workflow: search, describe, invoke, install/uninstall, subscribe/cancel, list_tools, report_bug, request_mcp, and the prompt library. It explains permission requirements, edge cases (credential/payment links), and flags for installed status. No output schema exists, so the description compensates by outlining what responses like connect/checkout links entail. This is thorough and covers all critical behavioral aspects.

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 23 parameters and 0% schema description coverage, the description must compensate. It does so by explaining the primary `action` enum in detail (search, describe, invoke, install, etc.) and indirectly clarifies related parameters like `mcp_id`, `tool_id`, `arguments`, and prompt-related fields within the context of each action. However, it does not systematically define every parameter (e.g., `limit`, `query`, `conversation`), though defaults and usage are implied. Since the key `action` parameter is thoroughly covered, it adds significant value, but some gaps remain.

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 that catalogs and runs MCPs/tools, with specific capabilities like search, describe, invoke, install, and prompt library access. It distinguishes itself from siblings (e.g., authenticate, connect) by covering all marketplace actions, and it explicitly differentiates invoke (one-off) from install (permanent). The purpose is unambiguous and detailed.

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 explicit guidance on when to use specific actions: 'action=search discovers MCPs by intent', 'describe returns one MCP's full profile', 'invoke RUNS that tool', and it contrasts invoke vs install: 'prefer invoke for a single/occasional use' and 'use install only to make an MCP PERMANENT'. It also notes permission requirements and the prompt library flow. This is clear when-to-use and alternatives coverage.

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