get_ecr_cleanup_recommendations

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

No annotations are provided, so the description carries full burden. It discloses that the tool scans regions and flags images, but does not explicitly state that it is read-only or that it does not modify resources. The cost context is helpful.

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 concise with no wasted words. The purpose is front-loaded, and examples are provided. Each sentence adds value.

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 description does not specify the return format or what information the recommendations contain (e.g., repository names, sizes, costs). Since there is no output schema, this is a gap, though the examples imply a natural language response.

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 coverage is 0%, so the description must compensate. It explains older_than_days as 'Flag untagged images older than this many days (default 90)' and regions as 'AWS regions to scan. Defaults to all opted-in regions.' This adds meaning beyond types and defaults, though could mention format for regions.

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 tool finds ECR repositories with old untagged images consuming storage, with a specific verb (Find) and resource (ECR repositories). It distinguishes from sibling tools by targeting a specific waste pattern for ECR.

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 includes example queries that imply usage, but does not explicitly state when to use this tool vs alternatives like scan_waste_patterns or cleanup_idle_resources. No 'when not to use' guidance is provided.

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