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

Annotations are minimal, and the description adds substantial behavioral context: writes 'require workspace owner/admin', invoke works even when the MCP is not installed, and auth/payment failures surface as connect/checkout links. It also discloses that invoke does not add the MCP to the toolkit, which is a key non-obvious behavior. No contradiction with the 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 a dense paragraph but front-loads purpose and core flow before diving into specific behaviors. Every sentence adds information, and the length is largely warranted by 14 actions and 23 parameters. Bulleted structure would improve scannability, but the text is still efficient and well-ordered.

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?

For a 14-action router with 23 parameters and no output schema, the description covers the main flows, permissions, invoke failure/link behavior, and the prompt-library subsystem. It leaves gaps around the 'resume' action, search/list_tools return formats, and the 'immediate' parameter, but overall it is notably complete given the tool's complexity.

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 description coverage and 23 parameters, the description carries a heavy burden. It does explain the action enum in prose and clarifies relationships like describe → tool_id and prompt_vars for get_prompt. However, many parameters (limit, query, immediate, conversation, tier_slug, request_details, cancel_reason) remain unexplained in both the schema and description, so parameter-level guidance is incomplete.

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' and explains it is both a catalog and execution layer ('the way to run them'). It enumerates the core flow (search → describe → invoke) and separates the prompt-library functionality, so the broad router purpose is unmistakable. It distinguishes itself from siblings by being the central MCP catalog/runtime rather than a single-purpose tool like authenticate or show_version.

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 rules: 'prefer invoke for a single/occasional use' vs. 'Use install only to make an MCP PERMANENT' and 'list_tools lists what is callable right now.' It also explains when invoke returns connect/checkout links and that the user should retry after acting. This is strong when-to-use and when-not-to-use guidance, including the alternative prompt-library flow.

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