guardrail_check

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

No annotations are provided, so the description carries the full burden. It only states the tool checks for dangerous patterns and PII but does not disclose behavioral traits such as whether it is read-only, destructive, requires authentication, or has side effects. This is insufficient for a tool that might be used in security-sensitive contexts.

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 two sentences, front-loaded with the purpose, and efficient. Every sentence adds value without waste.

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?

Given that an output schema exists (though not shown), the description does not need to explain return values. However, it lacks specifics about what constitutes 'dangerous patterns' or PII types, and does not indicate the output format or error behavior. Adequate but could be more comprehensive.

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 description coverage is 100% (one parameter 'text' with a description). The tool description adds no extra meaning beyond the schema's 'The input text to inspect.' Baseline is 3, and no additional value is provided.

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 whether a text string contains dangerous patterns or PII.' It uses a specific verb (check) and resource (text string for dangerous patterns/PII), and its use case ('pre-validate content before sending it to the API') distinguishes it from siblings like guardrail_check_payload.

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 context: 'Useful for Agents to pre-validate content before sending it to the API or including it in task descriptions.' However, it does not explicitly state when not to use it or mention alternatives like guardrail_check_payload, which may serve a similar purpose.

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