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

Discloses key behaviors beyond annotations: invoke works even when MCP is not installed, performs a one-off install, returns connect/checkout links when auth or payment is needed, and requires workspace owner/admin for writes. These operational details are not present in the sparse annotations (readOnlyHint: false, openWorldHint: true) and are critical for correct invocation.

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 justified by the tool's complexity (14 actions, two sub-features). The first sentence provides an immediate summary, and each subsequent sentence adds operational detail. Some sentences are long and packed, but they are all relevant; a bit of restructuring could improve scannability, yet it earns its length.

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?

Covers the majority of actions: search, describe, invoke, install, list_tools, subscribe/cancel, report_bug, request_mcp, and the prompt library. Explains return artifacts (connect links, checkout links, prompt slug). Omissions include the 'resume' action and some parameters (tier_slug, immediate), but the core workflow is fully specified. Given no output schema, this is quite complete.

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 adds substantial meaning to key parameters like action, mcp_id, tool_id, arguments, prompt_body, and prompt_vars. It explains the action flow (search → describe → invoke), but does not cover all 23 parameters (e.g., limit, immediate, tier_slug, resume) explicitly. Still, it compensates well for the schema's silence.

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 a clear verb+resource: 'The official mcp.ai marketplace — the in-platform catalog of every MCP/tool, AND the way to run them.' It specifies the exact scope (catalog + execution) and distinguishes itself from sibling tools by describing its unique position as the in-platform catalog and runtime.

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 instructions: 'Use install only to make an MCP PERMANENT... prefer invoke for a single/occasional use' and 'list_tools lists what is callable right now.' Also warns that writes 'require workspace owner/admin,' establishing clear prerequisites. This goes beyond simple capability listing to guide action selection.

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