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

The description discloses key behaviors beyond annotations: invoke runs uninstalled MCPs, returns connect/login links for credentials, returns checkout links for payments, and requires workspace owner/admin for writes. It also covers the prompt library's non-MCP behavior. No contradictions with annotations (readOnlyHint=false, openWorldHint=true) exist.

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 comprehensive, but somewhat lengthy. It is structured into clear sections (core flow, key caveats, prompt library) and every sentence adds value, though some could be tightened. The front-loaded core flow gives immediate orientation.

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 23 parameters, no output schema, and many actions, the description is remarkably thorough. It covers the primary flows, auth requirements, payment edge cases, role-based permissions, and the separate prompt library. It even notes the distinction between installed_in_toolkit vs installed_in_workspace, leaving little ambiguity for the agent.

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 does substantial work by explaining the semantics of action values (search, describe, invoke, install) and the purpose of mcp_id, tool_id, and arguments. It does not cover all 23 parameters (e.g., limit, immediate, tier_slug), but it conveys the essential parameter relationships for the core flow, earning above baseline.

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 its dual role as a catalog and execution engine. It distinguishes itself by listing concrete capability requests like 'find an MCP that does X' and 'consulta um CPF', and outlines the core flow of search → describe → invoke, making it unmistakable what the tool does.

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 when-to-use guidance, e.g., 'prefer invoke for a single/occasional use', 'Use install only to make an MCP PERMANENT', and 'instead' alternatives like using search_calls_extensive (implied by structure). It also explains when to use report_bug and request_mcp, giving clear decision criteria for the agent.

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