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

Beyond the sparse annotations (readOnlyHint=false, openWorldHint=true), the description reveals key behavioral traits: invoke works even when the MCP is not installed, returns connect/checkout links for auth/payment, writes require workspace owner/admin, and it explains the hidden one-off install behind invoke. This is rich, non-obvious behavioral disclosure.

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 organized into two coherent sections (marketplace and prompt library). It front-loads the core purpose and flows, and every sentence adds meaningful operational detail. While not terse, the length is justified by the tool's multi-action complexity.

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 tool with 14 actions, 23 parameters, and complex auth/payment behavior, the description is remarkably complete. It covers the full lifecycle: discovery, one-off invocation, permanent installation, billing, bug reporting, MCP requests, and the prompt library, plus permissions. No output schema exists, so the description carries the completeness burden and meets it.

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. It does explain the core parameters (action, mcp_id, tool_id, arguments) via the search/describe/invoke flow, but many parameters (resume, immediate, tier_slug, prompt_targets, prompt_category, conversation, etc.) remain undocumented. The description adds substantial context, but not full parameter-level semantics for all 23 params.

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, serving as both a catalog and execution layer for MCPs. It explicitly enumerates the core actions (search, describe, invoke, install, etc.) and the prompt library, distinguishing it from the unrelated sibling tools like authenticate or show_version.

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 decision guidance: 'prefer invoke for a single/occasional use' and 'Use install only to make an MCP PERMANENT'. It also gives a concrete workflow (search → describe → invoke), covers capability requests, and explains when to use report_bug vs request_mcp. This is exemplary usage guidance.

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