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

Annotations are minimal (destructiveHint false, readOnlyHint false), so the description carries the full burden. It discloses side effects: invoke runs one-off without adding to toolkit, writes require workspace owner/admin, invoke may return connect/checkout links. It also explains that search/describe flag installation state. This goes far beyond minimal disclosure and is transparent about returns and edge cases.

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 (multiple paragraphs) but densely informative. It is front-loaded with the core purpose and flow, then systematically covers behaviors, permissions, and the prompt library. Every sentence contributes value; no fluff. While not concise, its length is justified by the tool's 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?

No output schema, so the description must explain return behavior. It does: describe returns a full profile, invoke returns connect/checkout links, publish_prompt returns a share link. It also covers permission prerequisites and the open-world nature. The only gap is detailed return formats for each action, but given the breadth, it is adequately complete for agent decision-making.

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 has 23 parameters with 0% description coverage, so the description must compensate. It explains the core parameters (action, mcp_id, tool_id, arguments) through the flow, and touches on prompt-related parameters (prompt_slug, prompt_vars). However, it does not enumerate every parameter (e.g., limit, immediate, tier_slug), relying on defaults and action-specific context. For a 23-parameter tool, it provides enough semantic grounding but leaves some parameters implicit.

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's purpose: 'the official mcp.ai marketplace — the in-platform catalog of every MCP/tool, AND the way to run them.' It distinguishes from siblings by covering MCP discovery, execution, and prompt library operations, while siblings like authenticate, connect, and toolkit_info serve different roles. The scope is explicit and verbs are specific (search, describe, invoke, install).

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 guidance, including when to prefer invoke over install ('use install only to make an MCP PERMANENT... prefer invoke for a single/occasional use'), and outlines the core flow (search → describe → invoke). It also explains conditional behaviors (credential/checkout links, retry) and permission requirements, and covers related capabilities like prompt library usage. This thoroughly differentiates between actions and gives clear decision criteria.

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