AWS MCP Server

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

Annotations indicate readOnlyHint=false (mutation), openWorldHint=true (flexible inputs), idempotentHint=true (safe retries), and destructiveHint=false (non-destructive). The description adds minimal behavioral context beyond this, as 'Modify' implies mutation but doesn't detail effects like permission requirements, rate limits, or what 'modify' entails (e.g., partial updates). It doesn't contradict annotations, but provides little extra insight given the annotations cover safety and idempotency.

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 directly states the tool's function without redundancy. It's front-loaded with the core action and resource, making it easy to parse quickly. No extraneous words or unnecessary details are included.

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 (2 parameters with nested objects, no output schema) and annotations that cover safety (non-destructive, idempotent) but not full behavior, the description is minimally adequate. It specifies the action and region context, but lacks details on return values, error conditions, or how modifications interact with existing rules. For a mutation tool with moderate complexity, more completeness would be beneficial.

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 like 'CidrIpv4' and 'FromPort', but the top-level 'region' and 'SecurityGroupArgs' lack descriptions in the schema. The description mentions 'region' and implies rule modification, adding some context, but doesn't explain parameter relationships (e.g., that 'SecurityGroupRules' contains rule IDs and properties) or usage nuances. It partially compensates for the coverage gap but not fully.

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 ('Modify') and resource ('security group rule'), with the region as context. It distinguishes from siblings like 'authorize-security-group-ingress' or 'revoke-security-group-egress' by focusing on modification rather than authorization/revocation, though it doesn't explicitly differentiate from 'update-security-group-rule-descriptions-egress/ingress' which might have overlapping functionality.

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?

No guidance is provided on when to use this tool versus alternatives. It doesn't mention prerequisites (e.g., existing security group rules), compare to sibling tools like 'update-security-group-rule-descriptions-egress/ingress' or 'list-security-group-rules', or specify scenarios (e.g., updating CIDR ranges vs. descriptions). The description is purely functional without contextual advice.

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