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 discloses scan scope ('every message's text content') and what it looks for (credentials, PII), but says nothing about the output shape, whether it is read-only, or any rate/permission considerations.

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, front-loaded sentence with no wasted phrasing. It packs input format and detection targets together, but is dense enough that the read is slightly heavy for one clause.

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 simple one-parameter tool the description covers the input adequately, but with no annotations and no output schema the agent receives nothing about the return value or finding structure, leaving a real gap.

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% for the single `body` parameter, and the description merely restates the schema's own framing (a JSON object with messages/system). No additional syntax or format detail is added beyond what the schema already documents.

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 resource (a chat request body with a `messages` array and/or `system` field), plus the detection targets (credentials and PII). The input-format framing implicitly separates it from the sibling scan_text/scan_file variants without naming them explicitly.

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?

Provides clear context for invocation: run it on the request body 'before it would be sent to the model'. This is a meaningful pre-flight framing, though it names no explicit alternative among scan_text/scan_file/scan_directory.

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