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

The description discloses critical non-obvious behaviors beyond annotations: invoke works even when the MCP is not installed, runs one-off without bloating the tool list, returns connect/checkout links for auth/payment, and writes require owner/admin. It also clarifies installed_in_toolkit vs installed_in_workspace flags and prompt links opening without login, providing rich behavioral context not present in the 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?

The description is information-dense and front-loaded with core purpose and flow, earning each sentence's place given the many sub-actions. However, it is a single dense wall of text that could benefit from bullet points or section breaks for easier scanning. Still, it is appropriately sized for a 23-parameter mega-tool and contains no fluff.

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 complex dispatcher with no output schema and minimal annotations, the description is remarkably complete: it explains the end-to-end workflow, auth/paywall handling, permission requirements, one-off invocation semantics, install-vs-invoke tradeoffs, and the prompt library sub-feature. This fully addresses the tool's scope, external dependencies, and user retry flows.

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 description coverage, the description compensates well by explaining the main parameter roles: action's enum values (search, describe, install, invoke, etc.), mcp_id, tool_id, arguments, and prompt_* fields. However, not all 23 parameters are covered (e.g., limit, immediate, tier_slug, cancel_reason, prompt_targets, conversation), though many have intuitive defaults defined in the schema. This is a strong compensation given the tool's complexity, but leaves some 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 catalog and runner, covering both MCP discovery and execution (search/describe/invoke/install) plus a prompt library. It is specific about the resource (MCPs and prompts) and the actions performed, and it distinguishes itself from sibling tools like openfinance tools by focusing on the marketplace catalog and running capability, not on bank data.

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 provides explicit usage flow: search → describe → invoke, with clear directives to prefer invoke for one-off use and install only to make an MCP permanent. It also explains when to use list_tools, subscribe/cancel, report_bug, and request_mcp, and differentiates prompt library functions. This gives strong when-to-use guidance with exclusions and alternatives.

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