cloud-audit

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

No annotations provided, so description carries full burden. Discloses data source ('last scan'), data semantics ('correlated findings'), and return payload contents ('narrative, priority fix, and breach cost estimate'). Missing edge case handling (what if no scan exists?) and safety/permissions info.

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?

Three efficient sentences with zero waste. Front-loaded with action ('Get all...'), followed by behavioral definition, then output details. Appropriate length for complexity.

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?

Adequate for a zero-parameter read tool with output schema. Described return structure sufficiently without duplicating schema. Minor gap: doesn't specify behavior when no scan exists.

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?

Zero parameters present. Per rubric, 0 params = baseline 4. No parameter documentation needed.

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?

Clear specific verb 'Get' with resource 'attack chains'. Explicitly scopes to 'the last scan' and distinguishes from sibling get_findings by defining attack chains as 'correlated findings that form exploitable attack paths' (vs individual findings).

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?

Impls when to use by defining what attack chains are (correlated paths vs individual findings). Mentions temporal dependency on 'the last scan'. Lacks explicit 'use X instead for individual findings' statement, but context is clear enough to guide selection.

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