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

Annotations already mark it as read-only and idempotent, and the description adds behavioral detail: it replaces specific PII types with formatted [REDACTED_TYPE] placeholders. It also communicates safety for downstream operations, which supplements the annotations without contradiction.

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?

Three sentences, each earning its place: action, replacement behavior, and recommended use case. No filler or redundant restatement.

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 single-input utility with a straightforward output, the description plus annotations and output schema fully cover operation. It explains what the tool does, what it redacts, and when to use 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 coverage is 100%, with descriptions for input, types, and marker. The tool description merely lists the same entity types found in the schema and doesn't add new parameter-level semantics, so it meets the baseline.

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 a clear verb ('detect and redact') with a specific resource (PII from text) and enumerates the exact entity types covered. This distinguishes it from sibling text-analysis tools like detect_secrets or bias_detect, making the purpose immediately obvious.

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 explicitly recommends use before logging or sending to an LLM, giving a concrete scenario for when to use the tool. It doesn't name alternatives or exclusions, but the context is clear enough for an agent to choose this over other text utilities.

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