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

Discloses key behavioral traits beyond annotations: invoke runs tools one-off even without installation, returns connect/checkout links based on auth/wallet state, and writes require owner/admin. Also explains installed_in_toolkit vs installed_in_workspace flags. Contradicts no 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 justified by the tool's 23 parameters and many actions. It is front-loaded with purpose and organized into the core flow, edge cases, and prompt library. No redundant sentences; each clause adds value, though a structured list could improve scannability.

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?

Despite no output schema, the description covers critical runtime behavior: invoke return links, permanent vs one-off installation, permission requirements, and the prompt library flow. It doesn't describe return formats for every action, but the explanation is sufficient for a complex dispatcher tool.

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 schema description coverage at 0%, the description carries the burden for parameter meaning. It maps actions to intent (search→query, describe→mcp_id, invoke→tool_id/arguments) and prompt operations to concept, but leaves some params (limit, immediate, tier_slug, cancel_reason) implicit. Significant compensation but not exhaustive.

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' that catalogs and runs MCPs. It enumerates specific actions (search, describe, invoke, install, etc.) and distinguishes itself from siblings by framing the core flow and roles (catalog, runner, prompt library).

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 usage direction: 'prefer invoke for a single/occasional use' vs 'Use install only to make an MCP PERMANENT'. It also differentiates list_tools and explains when invoke returns connect/checkout links. States write actions require workspace owner/admin, giving clear access prerequisites.

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