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

Despite annotations being minimal (readOnlyHint false, openWorldHint true), the description discloses significant behavioral traits: invoke works even without installation, returns connect/checkout links for auth/payment, and notes that install/uninstall are write actions requiring owner/admin. It also separates the prompt library as a distinct capability, providing context beyond annotations without contradiction.

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, which is appropriate given the tool's complexity, but it is a single dense paragraph that could benefit from better structure (e.g., breaking out the prompt library into a separate section). Still, every sentence adds value and it front-loads the core purpose, so it's concise relative to the information needed.

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?

Given the tool's complexity (14 actions, 23 params, no output schema), the description is remarkably complete. It covers the core flow, invocation behavior, authentication and payment handling, permission requirements, and the separate prompt library. It omits some minor details (error handling, return formats) but provides enough for an agent to select and use the tool correctly in most scenarios.

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 23 parameters and 0% schema description coverage, the description compensates by explaining the key parameter 'action' and its enum values within the flow, plus how tool_id is used in invoke. However, it does not individually describe all parameters (e.g., arguments, immediate, tier_slug, prompt_*), though the workflow it outlines gives contextual meaning to the most critical ones, making it a strong but not exhaustive compensation.

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—a catalog and execution platform for MCPs. It states a specific verb+resource (search/describe/invoke) and distinguishes itself from sibling tools like authenticate, connect, and report_bug by outlining its comprehensive role covering both discovery and running of MCPs.

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: it details the core flow (search → describe → invoke), when to use invoke vs install (one-off vs permanent), and references other actions like list_tools, subscribe/cancel, and the prompt library (search_prompts, get_prompt, publish_prompt). It also notes that writes require owner/admin, giving clear context on alternatives and constraints.

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