scan_stopped_ec2

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

No annotations are provided, so the description must carry the full behavioral burden. It tells the agent the tool finds instances, suggesting a scan/read operation, but it doesn't disclose whether it performs any mutations, requires specific AWS credentials/permissions, or what the output looks like (e.g., a list of instance IDs and costs). Without annotations, this is a significant gap for a tool that likely accesses AWS.

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 of 8 words, efficient and focused on the core purpose. It gets to the point quickly and doesn't waste characters on filler. However, it could be slightly more helpful with additional context about the cost aspect, but for what it is, it's appropriately concise.

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 a simple schema (one param) and no output schema, so the description needs to be the main source of information. The description tells why to use it ('incurring EBS costs') but doesn't cover what the tool returns (list of instance IDs? total costs? a report?), how it behaves (does it only scan a single region?), or any prerequisites (like needing describe permissions). This is insufficient for an agent to fully understand the tool's output and side effects.

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 schema description coverage is 100%, so the single parameter 'region' is well-documented in the schema itself (type and example). The description doesn't add extra meaning about the region beyond what's in the schema, such as whether multiple regions are supported or if 'all' is a wildcard. Since the schema does its job, a baseline of 3 is appropriate.

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 verb 'find' and resource 'stopped EC2 instances' with a specific purpose ('still incurring EBS costs'). It stands out from siblings which target different resources (EBS, S3, security groups, IAM, CloudTrail), so an agent can likely distinguish it. However, it doesn't explicitly say it only lists instances (no action) and the word 'scan' in the name implies a read-only operation, which is clear enough but not as specific as some alternatives.

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 implies when to use it: when you need to identify cost-incurring stopped instances. However, it doesn't provide explicit guidance on when not to use it or direct to alternatives, such as using scan_unattached_ebs for volume-level costs or other scan tools for different resource types. The usage context is clear for the intended purpose but lacks exclusionary guidance.

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