sanitize_text

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

No annotations are provided, so the description carries the full burden of behavioral disclosure, but it only states the high-level action. It does not disclose the return shape (sanitized text only versus a structured report of detections), whether the input is mutated or a new string is returned, whether HASH is a one-way irreversible transform, or what REMOVE leaves behind in the text. For a tool that alters sensitive data, these are materially consequential gaps.

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 a single sentence that delivers the verb, resource, and use-phase in order of importance. There is no filler, no restating of the tool name, and no duplication of schema content. Every word earns its place.

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?

The tool has a moderately complex nested `rules` object (5 entity types × 3 modes), no output schema, and no annotations, yet the description does not explain what the tool returns, whether it mutates the input, or the behavior of the non-default modes. An agent would have to guess whether the result is redacted text alone or redacted text plus detection metadata — a real gap given nothing else compensates for it.

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%: both `text` and `rules` have descriptive text, and each nested entity type (NAME, EMAIL, PHONE, LOCATION, ID_NUMBER) documents its enum and meaning. The tool description itself adds no parameter-level information, so per the high-coverage baseline, a 3 is appropriate. The schema's own statement that rules 'Defaults to MASK for all types' already handles the default behavior.

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 uses specific verbs ('detect and redact') anchored to a concrete resource ('sensitive personal information from text'), and it adds the intended use phase ('before downstream processing'). It is not a tautology of the tool name. With no sibling tools provided, there is no differentiation to demonstrate, so it stops short of the full 5 by not actively distinguishing from possible alternatives.

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 only usage signal is 'before downstream processing,' which implies the tool should be invoked prior to other text-processing steps but never states this explicitly. No alternatives are named (there are no siblings), and no exclusion criteria are given — e.g., what to do if detection without redaction is needed. This is implied context rather than explicit when-to-use/when-not-to-use direction.

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