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

Beyond the generic annotations, the description reveals several important behaviors: invoke works even when the MCP is not installed and runs it one-off without bloating the toolkit; requires credential/login or payment, returning connect or checkout/top-up links; and that writes (install/uninstall/subscribe/cancel and the behind-the-scenes install from invoke) require workspace owner/admin. These details far exceed what readOnlyHint=false and openWorldHint=true convey, with no contradiction to 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 long but well-structured: definition → core flow → one-off execution behavior → install-vs-invoke guidance → permission requirements → prompt library addendum. Each section earns its place for a highly complex 23-parameter tool. Minor verbosity exists (e.g., the Spanish/Portuguese example "consulta um CPF" is illustrative but not essential), keeping it from a perfect score.

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 no output schema and 23 parameters, the description is unusually complete. It explains the main outputs: describe returns a full MCP profile with tools/pricing/auth, invoke returns connect or checkout/top-up links when needed, get_prompt fills variables, publish_prompt returns a shareable mcp.ai/p/<slug> link, and search/describe flag installed status. It also covers permissions and the permanent vs. one-off distinction. Remaining gaps (e.g., exact shape of search results) are minor given the description's breadth.

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 across 23 parameters, the description carries the full burden. It provides rich meaning for the most critical parameter, action, by explaining every enum value (search, describe, install, invoke, list_tools, search_prompts, etc.), and covers mcp_id, tool_id, arguments, prompt_slug, prompt_vars. However, some parameters (limit, immediate, tier_slug, conversation, prompt_targets, prompt_category, cancel_reason, report_context) are left implicit and only inferable from context, so the compensation is good but not complete.

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, specific definition: "The official mcp.ai marketplace — the in-platform catalog of every MCP/tool, AND the way to run them." It identifies the resource (marketplace) and its dual role as catalog and execution engine, then enumerates concrete capabilities (search, describe, invoke, install, prompt library). This clearly distinguishes it from sibling tools like authenticate, toolkit_info, 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 provides exemplary when-to-use guidance: it explicitly lays out the core flow "action=search discovers MCPs by intent → describe returns one MCP's full profile... → invoke RUNS that tool," and contrasts invoke vs. install: "Use install only to make an MCP PERMANENT in the active toolkit... prefer invoke for a single/occasional use." It also clarifies list_tools, request_mcp, and the prompt library functions, giving a complete decision framework.

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