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

The description discloses many non-obvious behaviors: invoke works even when the MCP is not installed, runs one-off without bloating the toolkit, returns a connect link when credentials are needed, returns a checkout/top-up link when the wallet is empty, and requires workspace owner/admin for writes. These details go far beyond the annotations (readOnlyHint: false, openWorldHint: true) and are critical for safe invocation.

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 but every sentence adds value: it covers the catalog concept, core flow, invoke's one-off behavior, connect/checkout links, install vs invoke, permission requirements, and the prompt library. It could be improved with bullet points or mini-headings, but given the tool's complexity (14 actions, 23 params), it remains concise and front-loaded with the most important information.

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 tool with 14 actions, 23 parameters, and no output schema, the description is remarkably complete. It covers the end-to-end flow, conditional behaviors (authenticated vs paid), permission requirements, and even the separate prompt library subsystem. It explains what to do when credentials are missing or wallet is empty, and clarifies 'installed_in_toolkit vs installed_in_workspace' flags. The only minor gap is a lack of pagination/return-format details, but since there is no output schema, the description does not explicitly need to cover that.

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 coverage, the description compensates significantly by explaining the central 'action' parameter (search, describe, invoke, install, etc.) and key fields like mcp_id, tool_id, arguments, and prompt_* parameters. It doesn't systematically describe all 23 parameters (e.g., cancel_reason, prompt_targets), but it gives enough semantic meaning for the primary workflow. A 4 is appropriate for substantial compensation, though not exhaustive.

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 clear statement: 'The official mcp.ai marketplace — the in-platform catalog of every MCP/tool, AND the way to run them.' It then details the core flow (search → describe → invoke) and explicitly lists each action (install, uninstall, subscribe, cancel, list_tools, etc.), making the tool's scope unmistakable. It also distinguishes itself from sibling tools by covering report_bug and request_mcp, and contrasts with the separate authenticate/connect tools implicitly.

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 usage guidance: 'Use install only to make an MCP PERMANENT in the active toolkit' and 'prefer invoke for a single/occasional use.' It also clarifies when to use search vs describe, explains that list_tools shows what is callable right now, and notes alternatives like request_mcp for building new MCPs. This goes beyond mere context and offers concrete decision rules.

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