prompt_leak_scanner__scan_messages

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

With no annotations, the description carries the full burden. It usefully specifies that it scans every message's text content and the system field, but does not say whether the operation is read-only, what the results look like, whether non-text content is ignored, or whether it blocks/returns findings only.

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?

A single sentence that front-loads the input format, the inspection target, and the purpose. Every clause adds useful information with no filler.

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 the nested body object, no output schema, and no annotations, the description does a good job defining what to pass and what gets inspected. It leaves out the return shape and any limitations on structured message parts, but the invocation-relevant context is largely present.

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% and there is one parameter, so the baseline is 3. The description adds meaningful detail beyond the schema: it identifies the expected OpenAI/Anthropic-style shape and clarifies that only message text content is scanned.

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?

States a specific verb (scan) and a specific resource (chat request body in OpenAI/Anthropic format), and the purpose (leaked credentials and PII). This clearly distinguishes it from sibling tools that scan raw text, files, or directories.

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?

Gives a clear use context: scan before the request would be sent to the model, i.e. a pre-flight check on structured chat payloads. It does not explicitly name alternatives like scan_text or scan_file, but the input scoping makes the intended use clear.

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