sweep_other_regions

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

No annotations are provided, so the description carries the full burden. It does not disclose whether the operation is read-only, whether it modifies anything, what the return format is, or any rate limits or region-specific behaviors. The term 'presence-check' suggests a listing operation, but this is not confirmed, and the meaning of 'forgotten resources' is left undefined.

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 sentence and is concise in length, but the ambiguity in 'every other' and the undefined 'forgotten' reduce its effectiveness. It is not front-loaded with the most critical clarifying information (e.g., what the region parameter does).

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?

The tool has no output schema and no annotations, so the description must cover return behavior and side effects. It does not explain what the tool returns (e.g., a list of resources, a summary count), whether it is safe to run repeatedly, or how the region parameter affects the scan. For a multi-region sweep, this is insufficient for an agent to call it correctly.

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?

The input schema describes the 'region' parameter as 'AWS region to scan', which conflicts with the tool description's 'every other enabled region'. The description does not clarify whether the parameter is the region to exclude, the starting region, or the only region scanned. With 100% schema coverage, the schema does provide a basic description, but the tool description introduces ambiguity, making the parameter's actual role unclear.

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 states a clear verb ('presence-check') and resource scope (EC2/EBS/RDS) across multiple regions, distinguishing it from sibling tools that target specific resource types. However, the phrase 'every other enabled region' is ambiguous—does it mean all regions except the one passed in the 'region' parameter, or all regions including it? This uncertainty reduces clarity.

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 the specific sibling scans (e.g., scan_stopped_ec2). It does not mention whether this should be a first pass before drilling into specific resources, or if it is a standalone audit. No exclusions or alternatives are given.

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