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

The description goes beyond the annotations (readOnlyHint: false, destructiveHint: false) by detailing that invoke runs tools even if not installed, returning connect/checkout links for auth/payment, and that writes require admin. However, it does not mention rate limits, error behaviors, or the exact consequences of install/uninstall beyond 'becomes permanent' and 'removed from toolkit.' The description does not contradict the annotations, and the mention of writes requiring admin is useful, but the depth is not exceptional.

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 and packed with information, but it is a single long paragraph with no structured breakdown (e.g., bullet points, sections) to ease scanning. It front-loads the general purpose and then flows into specifics, which helps, but the lack of structure may overwhelm agents. Each sentence adds value, but the overall length and stream-of-consciousness organization reduce clarity.

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?

Given the high complexity (23 params, 14 actions, interactions with MCPs and prompts, billing/auth flows), the description covers most critical guidance: how to search, describe, invoke, and install; mention of installed_in_toolkit/workspace flags; billing actions; and prompt library specifics. However, it does not describe output formats or error handling, and the absence of an output schema increases the need for return value clarification. Thus, not perfect but well above average.

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 coverage at 0%, the description carries the full burden. It explains key parameters such as action (via 'action=search', 'action=describe', 'action=invoke'), tool_id (select the right tool_id), arguments (implied by 'runs the tool'), and instant for specific actions. It also covers prompt-related parameters like prompt_slug, search_prompts, get_prompt, publish_prompt, and mention '{{variables}}' which maps to prompt_vars. For a tool with 23 parameters, this level of semantic detailing is excellent.

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 marketplace as the primary catalog and execution tool; it specifies that it covers a range of capability requests and describes the core flow (search, describe, invoke) and auxiliary actions. However, it does not explicitly distinguish from siblings like 'authenticate' or 'connect' beyond listing actions, and the broad scope (MCP management + prompt library) dilutes the single-purpose clarity.

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 strong guidance on when to use invoke vs install: 'Use install only to make an MCP PERMANENT... prefer invoke for a single/occasional use.' It also mentions list_tools for what is callable now, and subscribe/cancel for billing, and request_mcp for new MCPs. There is no explicit mention of alternatives among siblings, but the guidance for choosing among the tool's own actions is clear and direct.

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