AWS MCP Server

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

Annotations provide significant behavioral information (readOnlyHint=false, openWorldHint=true, idempotentHint=true, destructiveHint=false), so the description's burden is reduced. The description adds minimal context beyond this - it doesn't mention cost implications, that VPC creation is a foundational networking operation, or typical completion time. 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 extremely concise - a single sentence that directly states the tool's purpose. There's no wasted language or unnecessary elaboration, making it easy to parse quickly.

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 complexity of the input schema (12 nested properties) and absence of an output schema, the description is insufficient. While annotations cover safety aspects, the description doesn't address what happens after creation, error conditions, or the significance of VPC creation in AWS networking. For a tool with such complex parameters and no output documentation, more context would be helpful.

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 50% schema description coverage, the description mentions the 'region' parameter but doesn't explain the complex 'VpcArgs' object that contains 12 properties. While the schema documents these parameters well, the description doesn't add meaningful semantic context about parameter relationships (e.g., that CidrBlock is typically required, or how IPv4 and IPv6 parameters interact).

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 ('Create') and resource ('new VPC'), with the additional context of 'in the given region' that specifies a key operational parameter. However, it doesn't differentiate this tool from other VPC-related tools like 'create-subnet' or 'create-route-table' that might also create resources within a VPC context.

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 about when to use this tool versus alternatives. There's no mention of prerequisites (like needing AWS credentials), when not to use it (e.g., for existing VPCs), or how it relates to sibling tools like 'create-subnet' or 'delete-vpc' that operate on VPCs.

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