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

The description reveals non-obvious behaviors beyond the annotations: invoke runs tools not installed in a one-off manner without bloating the tool list; returns connect or checkout links for missing auth/payment; and notes that writes require workspace owner/admin. These details are not present in annotations (readOnlyHint=false) and are crucial for correct 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 lengthy but information-dense, front-loading the core purpose and flow before covering edge cases and secondary features. Some redundancy and run-on sentences ('without adding the MCP to the toolkit and without bloating the tool list') reduce readability, but the length is justified by the tool's complexity and multi-action nature.

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?

The description covers the major functional areas: search/describe/invoke, install/uninstall, subscribe/cancel, report_bug/request_mcp, and the prompt library, including permission and payment handling. Gaps remain for some enum actions like `resume` and parameter details such as `immediate` or `conversation`, and no output format is described (there is no output schema).

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 adds meaning by explaining the semantics of `action` values (search, describe, invoke, install, list_tools, prompt actions) and the data flow to `tool_id` and `arguments`. It also explains `prompt_slug` and {{variables}} for get_prompt. However, not all 23 parameters (e.g., `resume`, `immediate`, `conversation`, `tier_slug`) are individually explained, leaving some gaps.

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 explicitly states 'The official mcp.ai marketplace — the in-platform catalog of every MCP/tool, AND the way to run them.' It clearly defines the tool's role as both a catalog and an execution interface, and outlines the core flow (search → describe → invoke). This distinguishes it from sibling tools like authenticate/connect by positioning it as the central discovery and invocation hub.

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?

Provides concrete usage guidance: 'prefer invoke for a single/occasional use' and 'Use install only to make an MCP PERMANENT'. It also mentions alternatives like 'request_mcp asks us to build a NEW MCP when nothing fits' and 'list_tools lists what is callable right now', giving agents clear decision points for when to use this tool vs. other actions or tools.

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