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

Beyond the minimal annotations (readOnlyHint false, etc.), the description discloses critical behaviors: invoke runs a tool one-off without installing or bloating the list, writes require workspace owner/admin, and the one-off install behind invoke. This adds substantial context about side effects and prerequisites, and it does not contradict any annotation.

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 every sentence contributes value. It is structured logically: core flow, invoke's special behavior, install vs invoke, admin permissions, and the prompt library. The most important information is front-loaded.

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 highly complex tool with 23 parameters, no parameter descriptions, and no output schema, the description covers all major usage contexts: discovery, execution, installation, billing, reporting, and the prompt library. It even handles edge cases like missing credentials, empty wallet, and permission requirements.

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 coverage, the description carries the full burden. It clearly explains the action parameter and its enum values, including the flow between search/describe/invoke and the prompt library actions. Key parameters like mcp_id, tool_id, and prompt_vars are given meaning, though many others (limit, cancel_reason, conversation, etc.) are not explicitly described but are inferable from context.

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 identifies the tool as the official mcp.ai marketplace: the catalog of MCPs/tools and the way to run them. It names the core actions (search, describe, invoke, install) and distinguishes itself from siblings by covering both discovery and execution, including the 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?

The description provides explicit guidance: prefer invoke for single/occasional use, use install only for permanent toolkit additions, request_mcp when nothing fits, and report_bug for feedback. It also explains what invoke does when credentials or payment are needed, telling the agent to return a link and retry.

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