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

The description goes far beyond annotations to explain behaviors: invoke runs even when MCP is not installed, returns connect/checkout links for auth/payment, writes require owner/admin, and search/describe flag installed status. No contradiction with readOnlyHint=false, openWorldHint=true, etc. Provides extensive context on side effects and prerequisites.

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 a dense, single paragraph that packs a lot of information but is hard to scan. Every sentence adds value, but lack of formatting (bullets, line breaks) reduces readability. It is verbose but efficient; still, it could be restructured for better clarity without losing content.

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 is very thorough for a complex tool: covers flow, permissions, error handling (connect/checkout links), install vs invoke trade-offs, and the prompt library. However, it omits details on many parameters and does not specify return formats for actions, but given no output schema and multiple actions, it is largely complete. Only minor gaps in exact parameter usage keep it from a 5.

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 and 23 parameters, the description must compensate. It explains the meaning of key parameters (action, mcp_id, tool_id, arguments) implicitly through the flow, but leaves many (limit, query, immediate, tier_slug, prompt_*) unexplained. It provides some value but does not fully cover parameter semantics, falling short of the burden.

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 this as the official mcp.ai marketplace, covering both discovery and execution of MCPs, plus a prompt library. It distinguishes from siblings like authenticate or connect by focusing on catalog, running, installing, and billing. The verb+resource+scope is very specific and covers all actions.

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 guidance: a core flow (search → describe → invoke), clear distinction between invoke (one-off, no installation) vs install (permanent), and when to use search_prompts/get_prompt/publish_prompt. It also mentions requiring workspace owner/admin for writes, and lists alternatives for features like report_bug and request_mcp.

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