cloud-audit

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

With no annotations provided, the description carries the full disclosure burden. It effectively communicates the data source ('last scan') and output structure ('check ID, severity, resource...'), but omits operational details like error handling when no scan exists, caching behavior, or rate limiting constraints.

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 with purpose stated first, followed by output content summary, then parameterized details. The Args block is efficiently formatted, though the docstring style slightly duplicates structural information available in the schema property names.

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 existence of an output schema, the brief summary of finding contents is appropriate. The description adequately covers the temporal constraint (last scan dependency) and fully documents all three parameters. It misses only operational edge cases (e.g., empty scan results) for a complete picture.

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?

Despite 0% schema description coverage, the Args section fully compensates by providing complete semantics for all three parameters: enumerated severity levels (critical, high, medium, low), concrete service prefix examples ('iam', 's3'), and the limit's purpose and default value (20). This is exemplary compensation for schema deficiencies.

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 specific action ('Get findings') and scope ('from the last scan'), establishing this as a retrieval operation distinct from scanning or listing checks. However, it does not explicitly distinguish from siblings like get_attack_chains or differentiate when to use this versus other retrieval tools.

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?

While 'from the last scan' implicitly signals a temporal dependency on a prior scan operation, there are no explicit guidelines on when to use this tool versus alternatives like get_attack_chains, nor does it state prerequisites (e.g., requiring a completed scan) or exclusions.

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