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

The description reveals behaviors beyond annotations: invoke works even when the MCP is not installed and triggers a one-off install; it returns connect/checkout links for auth/payment flows; writes require workspace owner/admin; and the prompt library is a separate feature. No contradiction with annotations (readOnlyHint=false, openWorldHint=true, destructiveHint=false).

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 information-dense, front-loading the core purpose and then detailing workflow and key edge cases. It could be better structured with bullets, but every sentence contributes meaningful guidance for a complex multi-action tool.

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, no output schema, and multiple action modes, the description covers the main flows, auth/payment requirements, install vs invoke distinction, and the auxiliary prompt library. It gives enough context to select actions and understand return-link behaviors, making it complete for the tool's complexity.

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 well by explaining the core flow: action=search, describe returns profiles with tool_id, invoke runs with arguments, and prompt-related actions handle prompt variables. However, several parameters (like conversation, cancel_reason, prompt_targets, tier_slug) are not explained, so full compensation is incomplete.

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 mcp.ai marketplace catalog and execution engine, with a specific verb+resource structure. It distinguishes the main actions (search, describe, invoke) and contrasts it with siblings by explaining that it covers capability requests and runs tools, which is not indicated for other sibling tools.

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 explicit when-to-use guidance, e.g., 'prefer invoke for a single/occasional use' vs 'Use install only to make an MCP PERMANENT', and explains list_tools for what is callable right now. It also notes that search/describe flag installed status and that writes require owner/admin, offering clear decision criteria for action selection.

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