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

Given annotations only say non-read-only, non-idempotent, and open-world, the description adds critical behavioral context: invoke runs a one-off tool even if not installed, may trigger a hidden install, returns connect/checkout links for auth or payment and requires retry, and writes require workspace owner/admin. It also clarifies search/describe flag installation state and the prompt library's shareable links without login. This goes far beyond the structured annotations.

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 dense and informative but runs long as a single paragraph. It front-loads the core purpose and then elaborates on each action group, which is efficient given the tool's complexity. A more structured format (bullets or section breaks) would improve readability, but every sentence is substantive and no wasted words.

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?

With 23 parameters, no output schema, and sparse annotations, the description still covers the full action inventory, auth/permission requirements, edge cases (connect link, checkout/top-up, one-off install), and the separate prompt library. It gives the agent everything needed to decide which action to invoke and what to expect, making it highly complete for this complex tool.

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?

Schema description coverage is 0%, so the description must compensate. It effectively explains the core parameters (action, query, mcp_id, tool_id, arguments) and the prompt-related params via the prompt library explanation. However, it does not individually document all 23 parameters (e.g., tier_slug, cancel_reason, conversation, prompt_targets), leaving some ambiguity for less common fields. Still, it successfully maps the primary flows to the relevant 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 a precise definition: 'The official mcp.ai marketplace — the in-platform catalog of every MCP/tool, AND the way to run them.' It explicitly states it covers capability requests and distinguishes from siblings by detailing the search→describe→invoke core flow, which sets it apart from simpler tools like authenticate or report_bug.

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 each action: prefer invoke for single/occasional use, use install only to make an MCP permanent, use list_tools to see what is callable now, subscribe/cancel for billing, report_bug for feedback, request_mcp for new MCPs. It also contrasts with alternatives and gives concrete conditions (e.g., 'if the MCP needs a credential/login, invoke returns a connect link').

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