Metis · Data Guardian — Scan Outgoing

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

The description explains the action (checking for PII) and the return values (verdict, found, masked), but does not explicitly state whether the tool is read-only or if it has side effects. Given no annotations are provided, more explicit disclosure about safety traits would be beneficial, but the description still conveys core 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 concise (6-7 sentences), well-structured with a title, explanation, and a returns section. Every sentence adds value, and the purpose 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?

For a tool with a single input and a documented output schema (returning JSON with safe, found, masked), the description explains the output structure inline. It is complete and covers all necessary aspects for agent invocation.

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?

The only parameter, 'text', is clearly described in the description: 'The drafted response text to check.' This adds meaning beyond the schema, which only provides type and title. Since schema description coverage is 0%, the description fully compensates.

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's function: 'check a drafted response for leaked PII before it's sent.' It uses specific verbs and nouns ('check', 'drafted response', 'PII'), and distinguishes itself from sibling tools like 'check_data_safety' or 'scan_inbox' by emphasizing the output rail and complementing the read-side hook.

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 instructs agents to call this on 'any response that might contain individual-level data' and mentions it enforces the constitution's rule. While it does not explicitly state when not to use or list alternatives, the context is clear and sufficient for deciding when to invoke.

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