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

Annotations only flag readOnlyHint=false, openWorldHint=true, etc., but the description adds crucial behavior: invoke works even when MCP is not installed, returns connect/checkout links, modifies toolkit state on install/uninstall, and requires owner/admin for writes. It does not contradict annotations and fully discloses side effects and operational expectations.

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 densely packed and logically organized: high-level purpose, core flow, key invoke/install distinction, other actions, and prompt library. Every sentence adds value, but the single-paragraph format could benefit from bullet points or clearer separation of sections. For the complexity (14 actions), the length is justified but could be tighter.

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 (23 params, 14 actions, no output schema), the description covers the major aspects: usage flows, side effects, auth, billing, and prompt library. However, it does not explicitly state what each action returns (e.g., search output format, invoke response), which would be expected in the absence of an output schema. Overall, it is nearly complete but slightly short on return-value details.

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 has 0% description coverage, so the description must compensate. It explains the key 'action' parameter and how parameters like mcp_id, tool_id, arguments, and tier_slug fit the core flow, plus prompt-related params (prompt_slug, prompt_vars). While not every one of the 23 parameters is individually detailed, the description provides enough context to disambiguate primary use cases, leaving some minor gaps.

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, encompassing both catalog discovery and execution. It explicitly states the core flow (search→describe→invoke), distinguishes between one-off invocation and permanent installation, and names distinct sub-features like the prompt library. Verb+resource (marketplace catalog and runner) is specific and differentiates from all 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: 'prefer invoke for a single/occasional use', 'use install only to make an MCP PERMANENT', and explains when list_tools, subscribe/cancel, report_bug, request_mcp, and prompt library actions are appropriate. Also states auth requirements for writes. This exactly matches the intent of usage guidelines.

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