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

Beyond annotations (readOnlyHint=false, etc.), the description reveals key behaviors: invoke runs one-off without adding the MCP to the toolkit, auth/payment issues result in connect/checkout links with a retry mechanism, and writes (install/uninstall/subscribe/cancel and the one-off install behind invoke) require workspace owner/admin. It also clarifies that search/describe flag installation status, providing rich behavioral context.

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 justifiably so for a 23-parameter, multi-purpose tool. It is front-loaded with the core purpose and flow, uses arrows and emphasis ('KEY:') to structure key points, and avoids redundancy. Every sentence adds value, though it could be tightened slightly by omitting minor details like the full list of billing actions, which are already in the schema enum.

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 no output schema and 23 parameters, the description is remarkably complete. It covers the primary MCP discovery/execution flow, the one-off invoke exception, auth and payment edge cases, permission requirements, the prompt library, and even notes installed_in_toolkit vs installed_in_workspace. Minor omissions like the 'resume' action and detailed return formats are acceptable given the overall comprehensiveness.

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 parameter coverage, the description compensates thoroughly. It explains the meaning of each action enum value: search discovers, describe returns full profile (including tool id and params), invoke runs the tool, install makes permanent, list_tools shows callable tools, and prompt actions (search_prompts, get_prompt, publish_prompt) are all semantically described. It also ties key parameters like tool_id and prompt_vars to their roles in the flow.

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 states the tool is the official mcp.ai marketplace, defining its scope as the catalog of every MCP/tool and the way to run them. It enumerates specific capabilities (search, describe, invoke, install, prompt library) with distinct verbs and resources, and it naturally distinguishes itself from sibling tools by being the central hub for MCP discovery and execution.

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 lays out the core flow (search → describe → invoke) and provides direct comparisons: 'invoke works even when the MCP is NOT installed' vs 'Use install only to make an MCP PERMANENT', and 'prefer invoke for a single/occasional use'. It also names alternatives for specific needs: 'list_tools lists what is callable right now', 'subscribe/cancel handle per-MCP billing', 'report_bug sends feedback', and 'request_mcp asks us to build a NEW MCP when nothing fits'.

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