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

Even with annotations indicating readOnlyHint=false, the description adds substantial context: invoke runs one-off without installing, may return connect/checkout links, and writes require workspace owner/admin. It explains side effects (e.g., 'without bloating the tool list') and permission requirements, going far beyond the structural annotations.

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?

Despite containing a wealth of accurate information, it is delivered as one massive, unstructured wall of text with no line breaks, bullet points, or headers. While front-loaded with a strong opening sentence, the density makes it difficult for an agent to quickly extract key details. The information could be reorganized into sections (e.g., core flow, invoke behavior, prompt library) for better scannability.

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's complexity (23 parameters, 14+ actions), the description covers all major aspects: search/discovery, execution, installation, auth flows, payment handling, permission model, prompt library, and fallback mechanisms. It explains the full lifecycle from discovery to execution to management, making it a comprehensive reference for a highly complex meta-tool.

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 description coverage at 0%, the description carries the full burden and excels: it explains the meaning of the action enum values (search, describe, install, invoke, etc.) and the relationships between mcp_id, tool_id, and arguments. It clarifies the prompt library parameters (search_prompts, get_prompt, publish_prompt) and their purpose, compensating for the lack of schema-level documentation.

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 immediately identifies the tool as 'The official mcp.ai marketplace — the in-platform catalog of every MCP/tool, AND the way to run them.' It clearly distinguishes itself from siblings by describing its core flow (search → describe → invoke) and explicitly contrasts with alternatives like report_bug and request_mcp. The verb+resource is specific and the tool's role as a catalog and execution engine is unambiguous.

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?

Provides explicit decision guidance: 'Use install only to make an MCP PERMANENT in the active toolkit' and 'prefer invoke for a single/occasional use.' It also gives when-not-to-use guidance (e.g., 'if nothing fits' for request_mcp) and describes when prompt library actions are appropriate. This is a model example of usage context.

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