gateway_privacy_sanitize_text

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

The description discloses the irreversible nature of redaction ('irreversibly redact secrets'), which is a critical behavioral trait. However, annotations provide no safety hints (no readOnlyHint or destructiveHint), so the description carries the full burden but does not mention authorization requirements, rate limits, or the return format. It partially informs the agent but lacks depth.

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, efficient sentence with no filler. It front-loads the primary action ('Pseudonymize personal data') and includes the key qualifier 'irreversibly' upfront. Every word contributes to the meaning, making it highly concise.

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 privacy-critical tool with no schema descriptions and no annotation guidance, the description is insufficient. It does not explain the 'policy' parameter, the expected output, or any prerequisites (e.g., whether the input text is modified or returned sanitized). The tool's behavior is only partially covered, leaving significant gaps for an agent to call it 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?

The schema has 0% description coverage, so the description must compensate by explaining the parameters. It does not mention 'text' or 'policy' at all, nor does it explain what policy values mean or whether they are optional (though schema shows a default). The agent is left without any semantic context for the parameters.

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's function: 'Pseudonymize personal data and irreversibly redact secrets in text.' It uses specific verbs (pseudonymize, redact) and identifies the resource (personal data, secrets) with a clear scope (text). This distinguishes it from the sibling gateway_privacy_classify, which focuses on classification rather than transformation.

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 gives no guidance on when to use this tool versus alternatives. It does not mention conditions, exclusions, or when the sibling classify tool would be preferable. There is no explicit context for when an agent should call this vs. other privacy-related tools.

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