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

The description provides substantial behavioral detail beyond annotations: invoke works even when the MCP is not installed, returns a connect link if auth is needed, returns a checkout link if payment is required, and does not bloat the toolkit. It also discloses that writes require workspace owner/admin. These align with annotations (e.g., readOnlyHint=false) and add rich context 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 but dense and front-loaded, with the core purpose first, then the flow, caveats, and prompt library. Every sentence adds value, but the single-paragraph wall of text could be better structured with sections or bullet-like separation to improve scannability for an AI agent.

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, no output schema), the description covers the main flow, edge cases (auth, payment, not installed), permissions, and the prompt library. Minor gaps remain: the 'resume' action is not mentioned, and return value shapes are not described, but overall the description is sufficient for an agent to select and invoke the tool.

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 carries the full burden. It explains the meaning of action values, tool_id, arguments, prompt_slug, prompt_vars, and others through the described flows. However, several parameters like conversation, report_context, and cancel_reason are only inferable from context, not explicitly described, so it is not exhaustive.

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 specific verb+resource: 'The official mcp.ai marketplace — the in-platform catalog of every MCP/tool, AND the way to run them.' It clearly distinguishes from siblings by naming its core capability discovery and execution flow, and enumerates distinct actions like search, describe, invoke, and install.

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 explicitly states when to prefer invoke over install ('prefer invoke for a single/occasional use'), describes the core flow (search → describe → invoke), and identifies when each action is appropriate (e.g., 'report_bug sends feedback; request_mcp asks us to build a NEW MCP'). It also notes permission requirements for writes, giving clear when-to-use vs alternative guidance.

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