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

Goes well beyond annotations by disclosing that writes (install/uninstall/subscribe/cancel and the one-off install behind invoke) require workspace owner/admin privileges, that invoke runs a tool without installing it (one-off, without bloating the tool list), and that auth/payment failures return connect/checkout links for the user to complete. This adds critical behavioral context not present in annotations (readOnlyHint=false, openWorldHint=true).

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 effectively structured: it starts with the tool's identity and core flow, then covers invoke's key behavior, installation distinction, permission requirements, and ancillary features (prompt library). Each sentence contributes crucial information for a tool with 23 parameters and 14 actions. It could be tightened by removing some redundancy (e.g., repeated mentions of the prompt library), but it is appropriately sized for the complexity and front-loaded with the most important usage information.

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 highly complex tool with no output schema and 23 parameters, the description is exceptionally complete. It covers the core search-discover-invoke flow, the distinction between one-off invoke and permanent install, auth/payment failure handling, permission requirements (owner/admin for writes), the prompt library functions, and the full list of action enum values. This gives an agent virtually everything it needs to select the correct action and parameters for a given user request.

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?

Schema description coverage is 0%, so the description must compensate for parameter meaning. It explains the central 'action' parameter and its 14 possible values, and clarifies key parameters like mcp_id, tool_id, arguments, and prompt_* parameters in context. However, several parameters (limit, query, conversation, immediate, tier_slug, etc.) are not individually elaborated, leaving some ambiguity without external knowledge. The description does enough to make most parameters usable given the detailed flow guidance.

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, explicitly stating it covers capability requests like 'find an MCP that does X'. It distinguishes itself from sibling tools by detailing its core flow (search → describe → invoke) and contrasting invoke vs install, making it unambiguous what this tool does at a high level.

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 guidance: describes the recommended flow (action=search discovers MCPs, describe returns profiles, invoke runs), states when to prefer invoke over install ('prefer invoke for a single/occasional use'), and when install is appropriate (permanent addition to toolkit). It also covers alternative actions like list_tools, subscribe/cancel, and request_mcp, thus giving clear context for when to use this tool vs pursuing other paths.

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