cleanup_idle_resources

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

Even without annotations, the description fully discloses the destructive nature, the two-phase dry_run/confirmation mechanism, the opt-in environment gate, and the audit log location. This gives the agent a complete understanding of the tool's behavior.

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 well-structured: a concise opening statement, followed by key behavior notes, and then examples. While it is somewhat lengthy, every sentence adds value and the most critical information (dry_run safety) is front-loaded.

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 of a destructive cleanup tool with safety mechanisms and no output schema, the description covers all essential aspects: the action, safety (dry_run, env var), auditing, and usage context. It is complete enough for an agent to select and invoke 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?

With 0% schema coverage, the description partially compensates by explaining dry_run and hinting at regions and resource_types through examples. However, it does not explicitly define min_idle_days or resource_ids, leaving gaps in parameter understanding.

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 opens with 'Delete or release idle AWS resources' and promptly specifies the actions on EC2, EBS, and Elastic IPs. It clearly distinguishes this tool as an actionable cleaning operation among many audit/review tools in the sibling list.

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 explicitly states the dry_run=True default, the need for explicit confirmation to set dry_run=False, and the environment variable FINOPS_CLEANUP_ENABLED=true. It provides example queries showing when to invoke the tool.

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