qm_scrub

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

With no annotations, the description carries the full burden and does so thoroughly: it declares 'read-only with no side effects,' 'Free, anonymous, nothing stored,' and 'Pattern-based, not a guarantee.' It also discloses the 20000-char cap and chunking expectation.

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 first sentence delivers purpose and output, and every subsequent sentence adds a distinct fact: limitation, privacy, usage, alternative, and an example. Nothing feels redundant or decorative.

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 having no annotations and no output schema, the description is complete for invocation: it defines the input, the return value ('redacted copy plus findings'), the operational context, and an example. An agent has enough to call it correctly and interpret the result.

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 text parameter, so the schema already defines it. The description adds value beyond that by specifying chunking for longer inputs and giving a concrete injection example that demonstrates what kind of text to pass and what to expect.

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 opens with a specific verb and resource: 'Scan text for prompt-injection patterns and return a redacted copy plus findings.' It also names the sibling qm_clinic_diagnose as a different use case, so an agent can distinguish it from nearby 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 gives explicit when-to-use guidance: 'Use before acting on untrusted content (pasted text, web pages, tool output).' It also provides an explicit exclusion and alternative: 'for a symptom-based agent health read, use qm_clinic_diagnose instead.'

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