AWS MCP Server

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. While 'Describe' in AWS contexts implies a read-only operation, the description does not explicitly state it is safe, non-destructive, or disclose pagination behavior, rate limits, or what fields are returned (no output schema exists).

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 compact at one sentence. It is front-loaded with the primary operation and efficiently appends the filtering caveat. Every word earns its place, though brevity comes at the cost of missing contextual details.

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 simple read operation with three well-documented string parameters, the description minimally suffices. However, given the absence of an output schema, it should ideally describe the return structure or key attributes retrieved (e.g., state, subnet ID). It leaves significant AWS-specific behavioral context undocumented.

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?

Schema description coverage is 100%, establishing a baseline of 3. The description mentions 'optionally filtered by VPC,' which aligns with the vpc_id parameter, but largely restates what the schema already documents. It adds no semantic detail for the profile or region parameters beyond the schema definitions.

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 verb ('Describe') and resource ('NAT gateways'), and mentions the VPC filtering capability. However, it does not explicitly distinguish this from sibling VPC tools like describe_vpcs or describe_subnets, relying on the tool name to convey the specific resource type.

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 mentions that VPC filtering is optional ('optionally filtered by VPC'), implying when to use the vpc_id parameter. However, it provides no explicit guidance on when to choose this over similar VPC discovery tools, prerequisites (e.g., requiring the VPC to exist), or error conditions.

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