redact_pii

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

With no annotations, the description carries the burden well: it discloses that original values never leave the server, the exact placeholder format produced, and the three things returned (sanitized text, vaultId, placeholder+type pairs). It omits vault lifetime/expiry, error behavior, and the 50,000-character input limit, which are meaningful gaps for a security-sensitive transform.

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, front-loaded with the operation and mechanism, then return shape, then the restoration pointer. No redundancy and every sentence adds new 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?

There is no output schema, so the description must describe returns — it does so precisely, naming all three returned components and the placeholder format. For a two-parameter transform tool this is complete enough to 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?

Schema coverage is 100%, so both parameters are already documented, establishing a baseline of 3. The description goes further by tying vaultId to the round-trip workflow, making clear it must be reused in restore_pii — a semantic connection the schema alone does not spell out.

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?

States a specific verb (redact) plus resource (PII in text) and immediately names the mechanism (server-side vault) and the outcome (reversible round-trip with [REDACTED_<TYPE>_N] placeholders). This clearly separates it from sibling scan_pii (detection only) and restore_pii (the reverse direction).

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?

Explicitly tells the agent to call restore_pii with the same vaultId to recover originals, which establishes the correct follow-up path. It does not explicitly contrast with scan_pii for detection-only needs or state when not to use it, so it stops short of full when/when-not coverage.

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