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

Annotations are minimal (readOnlyHint false, destructiveHint false, openWorldHint true), so the description carries the full burden. It discloses that invoke works even on non-installed MCPs, returns connect/checkout links in specific scenarios, and that writes require workspace owner/admin. It also explains toolkit vs workspace installed flags, going well beyond 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 long but densely packed with unique information, with no redundant sentences. It front-loads the primary flow and then covers edge cases, permissions, and the prompt library. A more structured layout (e.g., bullet points) might improve scannability, but the content is concise relative to the tool's 14-action surface.

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 high complexity, the description covers all major behaviors: search/describe returns profiles, invoke returns links, list_tools enumerates callable tools, and the prompt library actions are described. It also addresses permissions, installed status flags, and the one-off vs permanent distinction, making it sufficient for safe and correct use.

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 23 parameters and 0% description coverage, the description must compensate. It does a strong job by explaining core parameters (action, tool_id, mcp_id, arguments, prompt_* variables) through the workflow examples. However, several parameters like immediate, tier_slug, request_details, and cancel_reason are never explicitly mentioned, so the agent must infer their meaning from names and enums alone.

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 immediately identifies the tool as 'the official mcp.ai marketplace — the in-platform catalog of every MCP/tool, AND the way to run them.' It enumerates the core flow (search → describe → invoke) and lists all action variants, clearly distinguishing marketplace from siblings like report_bug or connect. The purpose is unmistakable and highly specific.

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 explicit when-to-use guidance for each action: 'prefer invoke for a single/occasional use', 'Use install only to make an MCP PERMANENT', and it explains the core flow step-by-step. It also contrasts with list_tools and covers billing, reporting, and request actions, providing alternatives and exclusions.

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