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

With no annotations, the description fully discloses behavior: deterministic, sub-second, no network fetches, returns masked locators (never the secret), redacted copy, and cost (200c/call). This covers safety, performance, and data handling comprehensively.

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 front-loaded with purpose and usage, then details detection capabilities, output, and properties. It is efficient—every sentence adds information 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?

Despite lacking an output schema, the description explains the return values (risk level, detected classes with masked locator, redacted copy) and other traits (determinism, cost). It is fully sufficient for an agent to understand inputs and outputs.

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 schema includes a rich description for 'content' that matches the main description almost verbatim. Since schema_description_coverage is 100%, the description adds no extra value beyond what the schema already provides, resulting in baseline 3.

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 identifies the tool as a 'Leaked-credential guardrail for agents' and specifies the action (submit a blob, get a verdict). It lists specific detection targets and distinguishes itself from sibling guards by name and function.

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 provides concrete scenarios for use (about to commit, log, post, hand to another tool) and mentions limitations ('not a proof of cleanliness'). However, it does not explicitly compare to sibling tools or state when not to use.

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