stack_safety_verdict

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

Adds significant context beyond annotations: fusion of CVE batch with KEV catalog, conservative design, tier differences, token requirement, and call limits. No contradictions with annotations.

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?

Single paragraph that is dense but not overly long. Front-loads main purpose. Could be more structured, but information is well-packed with minimal fluff.

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?

Covers inputs, gate logic, tier behavior, and output components reasonably. Missing explicit output structure format, but given no output schema and low parameter count, description is largely complete.

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 100%, so baseline is 3. The description adds extra detail: 'preview' is free with caps, 'full' costs credit and includes evidence, and packages format is explained. Adds value beyond schema.

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?

Describes a specific verb ('get gate') and resource (AI software stack packages). Clearly states output: overall BLOCK/HOLD/PASS/UNKNOWN gate plus per-package verdict. Distinguishes from siblings by focusing on AI-stack safety, not general benchmark or SSVC verdicts.

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?

Explains when each gate applies (BLOCK on exploited with no fix, HOLD on known CVE, etc.) and tier limitations. However, no explicit comparison to alternative tools like ssvc_verdict or benchmark_trust_verdict.

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