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

Annotations indicate readOnlyHint=false and destructiveHint=false, which already signal mutability, but the description goes far beyond by explaining that invoke runs tools even when the MCP is not installed, returns connect/checkout links for auth/payment, and that writes require workspace owner/admin. It also notes installed_in_toolkit vs installed_in_workspace flags and the one-off install behind invoke. These behaviors are critical and not disclosed in the schema.

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 a single dense paragraph but well-structured: it opens with the core purpose, then details the invoke behavior, distinguishes install vs invoke, covers subscription and reporting actions, and finishes with the prompt library. Every sentence adds value, but the sheer length (due to the complexity of 14 action types) makes it less concise than ideal. The flow is logical and 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?

Given the tool has 23 parameters, 14 action types, and no output schema, the description provides a comprehensive overview of the main workflows (search, describe, invoke, install, prompts) and key side behaviors (auth links, wallet top-up, permission requirements). It does not detail return formats for each action or cover all edge cases, but it is sufficient for an agent to select and invoke the appropriate action in most scenarios.

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 description coverage, the description carries the full burden. It explains the meaning of key parameters like action (through its enum values), query, mcp_id, tool_id, and arguments, and describes prompt-related parameters (prompt_slug, prompt_vars, etc.) in the context of the prompt library. However, some parameters like immediate, tier_slug, and prompt_targets are not explicitly discussed, leaving minor gaps despite the strong overall contextual guidance.

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 this is the official mcp.ai marketplace—a catalog of every MCP/tool and a way to run them. It explicitly covers capability requests like 'find an MCP that does X' and explains the core flow (search → describe → invoke). It distinguishes this tool from siblings like authenticate or report_bug by focusing on marketplace operations, even if not naming them directly.

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 when-to-use guidance: 'prefer invoke for a single/occasional use; use install only to make an MCP PERMANENT' and explains that search discovers MCPs, describe returns profiles, and invoke runs tools. It also differentiates list_tools for what is callable right now and request_mcp for when nothing fits. Ownership requirements for writes are also stated, offering clear direction on action selection.

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