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

The description goes beyond the annotations by disclosing that invoke runs a tool even when not installed, that install makes an MCP permanent, and that writes require workspace owner/admin. It also describes the connect/checkout link behaviors, which are important side effects not captured in the schema or annotations.

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?

Although the description is a long paragraph, it is front-loaded with the core purpose and every sentence adds necessary detail about flows, exclusions, or the prompt library. There is no filler, and the dense format suits the tool's many actions.

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?

The description covers the primary workflows, auth requirements, billing edge cases, and the prompt library's response behavior. However, it does not detail the exact output structures for search or list_tools, and some param combinations are left to interpretation, so it is not fully exhaustive.

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?

The schema has 23 parameters with zero description coverage, but the description explains the purpose of key ones like action, mcp_id, tool_id, and prompt_slug. Many parameters remain undefined (e.g., limit, query, arguments, immediate), so it only partially compensates for the lack of schema documentation.

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 'The official mcp.ai marketplace — the in-platform catalog of every MCP/tool, AND the way to run them,' clearly establishing its dual role. It then enumerates the core action flow (search → describe → invoke) and separate capability areas like the prompt library, distinguishing it from sibling tools such as report_bug by noting that sub-action.

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 gives direct guidance: 'Core flow: action=search discovers MCPs by intent → describe returns... → invoke RUNS that tool.' It also states, 'prefer invoke for a single/occasional use' and 'Use install only to make an MCP PERMANENT,' providing clear when-to-use rules. It also explains fallback links for auth/payment, which helps the agent decide next steps.

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