AWS MCP Server

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

Annotations provide significant behavioral information (non-readOnly, openWorld, idempotent, non-destructive), so the description's burden is lower. The description adds no additional behavioral context beyond what annotations already declare - it doesn't mention AWS permissions needed, potential errors, rate limits, or what 'attach' actually entails operationally. However, it doesn't contradict the annotations either.

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, clear sentence with no wasted words. It's appropriately sized for a simple action and front-loads the essential information. Every word earns its place in conveying the core purpose.

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 networking configuration tool with no output schema, the description is insufficient. It doesn't explain what successful attachment means, what gets returned, error conditions, or how this fits into broader AWS networking. The annotations help but don't compensate for the lack of operational context in the description itself.

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 only 50% schema description coverage (the nested InternetGatewayArgs object lacks its own description), the description provides no parameter information to compensate. It doesn't explain the relationship between region and InternetGatewayArgs, what the DryRun parameter does, or the significance of the required IDs. The description adds zero semantic value beyond what's minimally present in the schema.

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 action ('attach') and target resource ('internet gateway to a VPC'), making the purpose immediately understandable. However, it doesn't differentiate from sibling tools like 'detach-internet-gateway' or explain how this differs from related networking operations like 'associate-route-table' or 'create-internet-gateway'.

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 no guidance on when to use this tool versus alternatives. It doesn't mention prerequisites (e.g., needing an existing internet gateway and VPC), when this operation is appropriate in network setup workflows, or what happens if the gateway is already attached. The agent receives no usage context beyond the basic action.

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