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

Beyond the sparse annotations, it discloses that invoke runs a tool one-off even when not installed, returns a connect link when credentials are needed, and returns a checkout/top-up link when the wallet is empty before retrying. It also states that writes require workspace owner/admin, which the annotation flags do not convey.

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 dense; each clause covers a distinct action, flow step, or constraint (e.g., 'without bloating the tool list', 'opens without login'). It is front-loaded with the tool's identity and core flow, and the KEY highlight draws attention to the most important behavior.

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, 23-param tool with no output schema, it covers the central round trip (discover → describe → invoke), auth/payment fallbacks, install-vs-invoke tradeoffs, permissions, and the entire prompt-library subfeature. Notable gaps are the 'resume' action and several optional params like immediate and tier_slug, which are never mentioned.

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, the description compensates for the core workflow by explaining action, query ('find an MCP that does X'), mcp_id/tool_id selection, prompt_vars filling, and prompt_slug links. However, ancillary parameters such as limit, immediate, tier_slug, message, conversation, report_context, and prompt_targets receive no explanation, so the compensation is only partial.

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 by defining the tool as the mcp.ai marketplace catalog and execution layer, then enumerates its actions and the core flow (search → describe → invoke). Despite the generic name, an agent can tell this is the discovery-and-runtime tool for MCPs and prompt-library operations, clearly distinct from the domain calculators listed as siblings.

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?

It gives explicit routing rules: 'prefer invoke for a single/occasional use' vs 'Use install only to make an MCP PERMANENT', and 'request_mcp asks us to build a NEW MCP when nothing fits.' It also separates prompt-library actions from MCP actions, so the agent knows when to call search_prompts/get_prompt/publish_prompt.

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