ai_redactor

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

Beyond annotations, the description discloses the permanent/destructive nature of the operation, the ability to stage before applying, and that it reads/writes locally or from sandbox. It does not contradict annotations. Adds context on types of content detected and default behavior when neither stage nor apply is set.

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 well-structured with a clear opening sentence, bullet points for content types, and clear paragraphs for stage/apply workflow. Every sentence adds value, no fluff. Appropriate length.

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 tool's moderate complexity and lack of output schema, the description covers the essential aspects: what it does, parameters, workflow, and file handling. It is sufficient for an AI agent to understand when and how to use it effectively.

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%, so baseline is 3. The description adds value by explaining the stage/apply workflow, providing concrete examples for the criteria parameter, and clarifying file path resolution. This meaningfully supplements the schema.

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 detects and permanently redacts sensitive content using the Nutrient AI Redaction API. It specifies the action (detect and redact) and the resource (sensitive content), and lists types of content it handles. It is distinct from sibling tools like document_processor or document_signer.

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 explains the default behavior (detect and apply) and provides explicit workflow for staging and applying redactions using the stage and apply flags. It mentions mutual exclusivity. While it does not directly compare to siblings, the tool's unique purpose is clear enough. Could be improved by stating when not to use it, but overall good guidance.

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