aws_call

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

Despite no annotations, the description fully discloses all behavioral traits: auto-pagination for reads, read-only default, need for mutate flag, destructive op refusal and two-phase confirm, region/account pinning, and max_items cap. No contradictions.

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 coherent paragraph that covers all critical aspects without redundancy. Slightly dense but still readable; could be improved with bullet points but remains concise and front-loaded with the main purpose.

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 8 parameters, no output schema, and high complexity, the description covers almost all necessary context: parameter roles, auto-pagination, safety guards, and two-phase destructive confirm. Lacks explicit mention of response format, but for a generic passthrough the boto3 response is assumed.

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?

With 100% schema coverage, baseline is 3. The description adds value by clarifying operation is snake_case, params uses PascalCase keys, explains auto-pagination behavior, and details the confirm parameter's two-phase process. Exceeds baseline by providing usage context.

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 defines the tool as a generic passthrough for AWS read operations not pre-wrapped, listing example operations (DescribeSecurityGroupRules, GetIPSet, etc.) and distinguishing it from sibling tools that are specific wrappers. It also explains mutating and destructive modes, making purpose unambiguous.

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?

Provides explicit guidance: use for any Describe*/Get*/List*/Filter*/Lookup* operation not pre-wrapped; mutating ops require mutate=true; destructive verbs require special config and a two-phase confirm. Directly tells when to use and when not, with clear alternatives implied by sibling separation.

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