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

Annotations only state non-read-only, non-idempotent, non-destructive, and open-world. The description adds substantial behavior: invoke works for non-installed MCPs, returns connect links for auth and top-up links for empty wallets, mentions owner/admin permission for writes, and notes that install adds tools permanently while invoke runs one-off without bloating the list. No contradiction with 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 every sentence adds distinct value for a 14-action tool. It is front-loaded with the core purpose and progresses logically from core flow to key invoke behavior, install vs invoke, then auxiliary actions and the prompt library. Could be improved with structural separation, but remains efficient for its complexity.

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, 14 actions, no output schema, and minimal annotations, the description covers the central search→describe→invoke flow, permission requirements, and one-off vs permanent semantics. Gaps remain: the 'resume' action is not explained, the 'immediate' flag and pagination limits are not documented, and exact return shapes are not described, leaving some uncertainty for edge-case actions.

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 by explaining the main action parameter and the roles of mcp_id, tool_id, arguments, and prompt-related fields in the flow. However, many parameters like limit, immediate, tier_slug, cancel_reason, report_context, request_details, prompt_targets, conversation, and prompt_tool are not semantically explained, requiring agent inference.

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 opening sentence clearly identifies the tool as 'the official mcp.ai marketplace' and the way to run MCPs, with a specific verb+resource. It enumerates the core actions (search, describe, invoke) and distinguishes this from sibling tools like authenticate, connect, and show_version by focusing on catalog/search/run capabilities.

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 gives explicit when-to-use guidance: 'Use install only to make an MCP PERMANENT', 'prefer invoke for a single/occasional use', and 'list_tools lists what is callable right now'. It also clarifies when to use subscribe/cancel, report_bug, request_mcp, and the prompt library actions, forming clear decision rules between alternatives.

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