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

Despite annotations indicating readOnlyHint:false and openWorldHint:true, the description adds substantial behavioral detail: it explains that invoke runs tools on a one-off basis without adding to the toolkit, that it returns connect links for missing credentials and checkout/top-up links for insufficient wallet, and that writes require admin. It also notes that search/describe flag installation state. This goes well beyond annotations and clarifies side effects.

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 (over 300 words) and dense, covering numerous actions and edge cases. It is structurally logical (starts with purpose, then core flow, then exceptions, then prompt library) and every sentence carries information, but it is not concise. It is front-loaded with the key purpose and flow, but could be more compact. Given the tool's complexity, the length is somewhat justified but not ideal.

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 multi-action tool with 23 parameters and no output schema, the description is remarkably complete. It covers the entire workflow, exception handling (credentials, wallet), permissions, the prompt library, and even distinguishes installed state flags. It explains the billing actions and report paths. It provides sufficient context for an agent to decide which action to use and what to expect, leaving no major gaps.

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 zero schema descriptions, the description must compensate for parameter meaning. It explains the core flow and mentions key parameters (action, mcp_id, tool_id, arguments, message) and outlines prompt library actions (search_prompts, get_prompt, publish_prompt). However, it does not explicitly cover all 23 parameters (e.g., limit, query, immediate, tier_slug, prompt_vars) leaving some vagueness, though the context implies their usage. It adds meaning for the primary parameters but not exhaustively.

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 as the official mcp.ai marketplace, covering both MCP discovery and execution plus a prompt library. It distinguishes itself from siblings like 'authenticate' and 'connect' by explicitly listing its core flow (search → describe → invoke) and its unique feature of running MCPs without installation. The verb is specific ('is', 'covers', 'runs') and the resource is well defined.

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 when-to-use guidance: 'prefer invoke for a single/occasional use', 'use install only to make an MCP PERMANENT', and explains that invoke works even when MCP is not installed. It also mentions prerequisites like permissions ('require workspace owner/admin') and gives exact scenarios for search/describe vs install. Alternatives are named (like 'request_mcp asks us to build a NEW MCP when nothing fits').

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