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

The description goes well beyond annotations by disclosing that processing is rule-based, no model sees input, and same values map to the same placeholders for restorability. These details add meaningful behavioral context beyond the readOnlyHint and idempotentHint annotations.

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?

Two compact sentences, front-loaded with the core action and return value, then adding a key behavioral guarantee. No filler or repetition of schema/annotations.

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 two-parameter tool with a rich output schema and strong annotations, the description fully covers the core function, privacy model, deterministic mapping, and restoration capability. It is complete for an agent to select and invoke correctly.

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?

Input schema covers both parameters with clear descriptions (text, optional 'only' subset), so baseline is 3. The description adds no extra parameter-level details, but it does list the entity types that will be redacted by default, which indirectly informs the 'only' filtering 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 a specific verb ('Strip') and enumerates the exact resource types (emails, phone numbers, ID numbers, API keys, etc.), making it clear what the tool does. It also explicitly differentiates from sibling tools like diff_text and json_format by focusing on redaction and returning a restoration mapping.

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 phrase 'before sending text on' establishes a clear use case, and 'Rule-based only — no model sees the input' provides important context about when this is preferable. It does not explicitly name alternative tools for exclusion, but the sibling list contains no other redaction tool, so distinction is inherent.

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