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

Beyond annotations, the description reveals side effects: invoke performs a 'one-off install', returns connect/checkout links when needed, and writes require 'workspace owner/admin.' It also explains that search/describe flag installed_in_toolkit vs installed_in_workspace, and that publish_prompt yields a public link. These behavioral details go well beyond the minimal annotation hints and are crucial for safe 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 dense but every sentence carries purpose—covering core flow, edge cases, auth restrictions, and prompt library. It is front-loaded with the main purpose, and while it is a single block of text rather than structured bullets, it avoids fluff and stays on-topic. The only slight deduction is for being overly long and not using lists to improve scanability.

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 such a complex tool (14 actions, 23 params, no output schema), the description covers a lot: core flow, invoke edge cases, auth, and prompt library. However, it omits the 'resume' action entirely, doesn't describe return formats for search/describe, and lacks explicit action-to-parameter mapping. These are meaningful gaps for an agent to correctly construct invocations, so it is not fully 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?

The description thoroughly explains the action enum values (search, describe, invoke, etc.) but never maps specific parameters to those actions. For example, it doesn't say that invoke needs tool_id and arguments, describe needs mcp_id, or what immediate, conversation, or cancel_comment do. Since schema description coverage is 0% across 23 parameters, the description fails to compensate, leaving agents to guess parameter requirements for each action.

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 in-platform catalog of every MCP/tool, AND the way to run them.' It distinguishes it from siblings by outlining the core flow (search → describe → invoke) and additional prompt library features. This is a specific, action-oriented definition that separates it from tools like connect, authenticate, and report_bug.

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 guidance: 'prefer invoke for a single/occasional use' versus 'use install only to make an MCP PERMANENT in the active toolkit.' It also spells out the core flow and lists each action's purpose, such as 'list_tools lists what is callable right now' and 'request_mcp asks us to build a NEW MCP when nothing fits.' This provides clear when-to-use and alternative direction.

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