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

Annotations already declare destructiveHint=true, idempotentHint=true and openWorldHint=true, so the safety profile is covered. The description adds real value beyond them: it states the return content (redacted text plus preview), the external-boundary guarantee (no send to Claude Legal), and an auth prerequisite ('Requires tools.text'). It does not explain irreversibility or whether the source is modified.

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 short sentences, zero padding, and the core capability is front-loaded before the boundary and workflow conditions. Every sentence carries distinct information.

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?

Return values are adequately covered despite no output schema, and the auth/workflow context is present. The main gap is the undocumented entity_types vocabulary, which an agent needs in order to call the tool correctly for a 0%-coverage schema.

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 0% for two required parameters. The phrase 'by entity type' hints that entity_types controls which entities are redacted, but no valid entity values or format are given, and the text parameter's accepted input is never addressed. The description only partially compensates for a total schema documentation gap.

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 names a specific verb (redaction) and resource (personal data in contracts, emails, transcripts) with scope qualifier 'by entity type.' It is clear what the tool does, though it never names the closest sibling anonymize_document, so sibling differentiation is only implicit.

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 gives concrete workflow routing: 'Does not send content to Claude Legal' and 'If Claude Legal is enabled, wait for the user to confirm then call review_with_claude_legal.' That is explicit sequencing against a named sibling. It stops short of saying when to prefer this over anonymize_document.

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