AWS MCP Server

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

Annotations provide readOnlyHint=false (mutation), openWorldHint=true (supports many parameters), idempotentHint=true (safe to retry), and destructiveHint=false (non-destructive). The description adds minimal behavioral context by specifying the resource types (Gateway/Interface endpoints) and region scope, but doesn't elaborate on permissions, rate limits, or mutation effects beyond what annotations imply. No contradiction with annotations 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 a single, well-structured sentence that efficiently conveys the core purpose: action, resource, identifier, and scope. There is no redundant information or unnecessary elaboration, making it easy to parse and front-loaded with essential 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 mutation tool with 2 parameters (one nested with many sub-parameters), 50% schema coverage, no output schema, and annotations covering basic behavioral hints, the description is insufficient. It lacks critical context such as what fields are updatable, potential side effects, error conditions, or example usage, leaving significant gaps for an agent to understand how to invoke it effectively.

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 50%, with detailed descriptions for nested parameters in VpcArgs but none for the top-level 'region' parameter. The description mentions 'region' and 'VPC endpoint ID', aligning with schema parameters, but adds no additional semantic context (e.g., format examples, constraints, or interactions between parameters). With moderate schema coverage, the baseline score of 3 is appropriate.

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 ('Update') and resource ('VPC endpoint') with specific types mentioned (Gateway endpoint, Interface endpoint). It includes the required identifier (VPC endpoint ID) and scope (region). However, it doesn't differentiate this tool from sibling tools like update-vpc-attribute or update-subnet-attribute, which are also AWS VPC update operations.

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 VPC endpoint), exclusions (e.g., what cannot be updated), or suggest sibling tools for related operations like creating or deleting VPC endpoints. The agent must infer usage from the tool name alone.

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