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

Despite having annotations (readOnlyHint false, openWorldHint true), the description adds substantial behavioral context beyond them. It reveals that invoke works even for uninstalled MCPs, runs one-off without bloating the toolkit, returns connect/checkout links for auth/payment, and requires workspace owner/admin for writes. These details are not present in the annotations, so the description carries significant extra value without contradicting any annotation.

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 a single, dense paragraph exceeding 200 words with no bullet points, headings, or any structural segmentation. While every sentence carries information, the lack of organization makes it hard to scan and parse. It is not concise; it could be split into sections per action or flow without losing content. The front-loading is adequate but the overall structure is poor.

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 (14 actions, 23 parameters, no output schema), the description covers the vast majority of relevant context: all actions, their relationships, permission requirements, billing, auth flows, and the prompt library. It does not describe return value formats, but since no output schema exists, this is a minor omission. It adequately addresses most aspects an agent would need to know to select and invoke the tool 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?

With 0% schema parameter coverage, the description must compensate. It does explain the meaning of key parameters implicitly through action descriptions (e.g., mcp_id for describe, tool_id and arguments for invoke), and it describes the prompt-library parameters (prompt_slug, etc.). However, it doesn't systematically define all 23 parameters; obscure ones like 'immediate', 'tier_slug', 'cancel_reason', and 'prompt_targets' are not explicitly explained beyond their names. The description gives functional context but leaves gaps for parameters not tied to a described action.

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 explicitly states the tool's role as 'The official mcp.ai marketplace — the in-platform catalog of every MCP/tool, AND the way to run them.' It enumerates all 14 actions and explains their functions, clearly distinguishing it from sibling tools like 'authenticate' or 'toolkit_info' by positioning it as the central hub for discovering, running, and managing MCPs. The verb+resource structure is specific and unambiguous.

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 an explicit core flow: 'action=search discovers MCPs by intent → describe returns one MCP's full profile... → invoke RUNS that tool.' It also gives clear when-to-use guidance, such as 'prefer invoke for a single/occasional use' versus 'Use install only to make an MCP PERMANENT.' It covers exclusions and prerequisites, including permission requirements for writes and the behavior of invoke when credentials or payment are needed.

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