AWS MCP Server

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

Annotations already provide key behavioral hints: readOnlyHint=false (mutation), destructiveHint=false (non-destructive), idempotentHint=true (safe to retry), and openWorldHint=true (flexible inputs). The description adds that this updates specific VPC attributes by ID in a region, which provides operational context. However, it doesn't disclose important behavioral details like authentication requirements, rate limits, error conditions, or what happens when only some attributes are specified.

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, efficient sentence that packs essential information: action, resource, specific attributes, and key parameters. Every word earns its place with no redundancy or fluff. It's appropriately sized for a tool with clear parameters and good annotations.

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 no output schema, the description is minimally adequate. Annotations cover safety profile (non-destructive, idempotent), and the description specifies what gets updated. However, it lacks information about return values, error cases, or side effects. Given the complexity of AWS VPC operations and the nested parameter structure, more context would be helpful for safe invocation.

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% (region parameter has description, VpcArgs object doesn't). The description mentions 'VPC ID' and 'region' but doesn't explain the nested structure of VpcArgs or that only VpcId is required while the three attribute objects are optional. It lists the three attribute names, which helps, but doesn't clarify that each requires a Value boolean sub-property. The description adds some value but doesn't fully compensate for the schema coverage gap.

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'), resource ('VPC attribute'), and specifies the three specific attributes that can be modified. It distinguishes this from sibling tools like 'update-subnet-attribute' by focusing on VPC-level attributes rather than subnet-level ones. However, it doesn't explicitly contrast with other VPC modification tools like 'update-vpc-endpoint'.

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), when this operation is appropriate versus creating a new VPC, or how it differs from other update operations in the sibling tool list. The agent must infer usage context 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.