scan_outgoing

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

With no annotations, the description fully discloses behavior: it checks for PII, returns a verdict, found items, and a masked version. It also explains it enforces a constitutional rule and is non-destructive. The output JSON schema is clearly outlined.

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, with a clear lead sentence followed by structured Args and Returns sections. Every sentence adds value without redundancy.

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 one parameter and no annotations, it provides complete information: what it does, when to use it, and what output to expect (including JSON structure). No gaps remain.

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 single parameter 'text' is described as 'The drafted response text to check,' adding essential meaning beyond the schema's type-only definition. Schema coverage is 0%, so 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 purpose: 'check a drafted response for leaked PII before it's sent.' It uses a specific verb ('check') and resource ('drafted response'), and distinguishes itself as the 'output-side complement to the read-side hook,' setting it apart from similar scanning 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?

It provides clear usage context: 'call this on any response that might contain individual-level data' and mentions enforcement of a no-PII rule. However, it does not explicitly state when not to use this tool or mention alternative sibling tools like 'check_data_safety' or 'anonymize_text'.

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