AWS MCP Server

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

Annotations indicate this is a mutable, non-destructive, non-idempotent operation (readOnlyHint: false, destructiveHint: false, idempotentHint: false), but the description doesn't add behavioral context beyond 'Create'. It fails to disclose that this generates a new key pair (likely with a private key returned), requires AWS permissions, may have rate limits, or that 'DryRun' parameter allows permission checks without actual creation. With annotations covering basic traits, the description adds minimal value.

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 with zero wasted words, front-loading the core action ('Create a key pair') and essential context ('in the given region'). Every word earns its place, making it highly concise and well-structured for quick understanding.

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 tool's complexity (2 parameters with nested objects, 50% schema coverage, no output schema, and annotations providing basic hints), the description is inadequate. It doesn't explain what the tool returns (e.g., private key material), behavioral nuances like idempotency or permissions, or how to handle parameters like 'DryRun'. For a creation tool with significant parameter details, more context is needed to be complete.

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 parameters like 'region' and 'KeyPairArgs' documented in the schema but nested details (e.g., 'KeyName', 'DryRun') partially covered. The description mentions 'region' but doesn't explain parameter meanings beyond what the schema provides, such as the purpose of 'DryRun' or 'KeyType' options. It compensates slightly by implying regional context but doesn't fully address the 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 ('Create') and resource ('key pair') with regional context ('in the given region'), making the purpose unambiguous. However, it doesn't differentiate from sibling tools like 'import-key-pair' or 'delete-key-pair', which would require mentioning this creates a new key pair from scratch rather than importing or deleting existing ones.

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 like 'import-key-pair' or 'delete-key-pair', nor does it mention prerequisites such as AWS permissions or regional availability. It lacks explicit when/when-not statements or named alternatives, leaving usage context unclear.

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