pii_redact

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

With no annotations, the description carries the full burden and does so richly: it splits deterministic detection (emails, checksum-verified IBANs, Luhn-verified cards, phones, IPs) from LLM detection (names, addresses, birth dates, IDs), discloses stable placeholders plus a restorable mapping, the 8,000-char cap, language scope, injection resistance, cost, and p99 latency.

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?

One dense paragraph, but it is front-loaded with the core purpose and every clause (limits, cost, latency, injection note) carries operational value. Slightly run-on, but nothing is filler.

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 5-parameter transformation tool with no output schema, the description covers the return (mapping), the modes, the size limit, and detection behavior; the input schema already documents each parameter, so nothing an agent needs to invoke it correctly is missing.

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 baseline is 3, but the description adds real meaning beyond the schema: the mapping exists so you can restore values later, and mode supports mask/remove alongside the default placeholder. keep, types, and the default exclusion of ORGANIZATION/URL are left to the schema.

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 and resource ('PII redaction... remove personal data from text') and immediately frames the concrete contexts (model input, logs, tickets, datasets). It is clearly distinct from neighbors like privacy_check or prompt_injection_check, which audit rather than transform.

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 'before it goes to another model, a log, a ticket system or a dataset' clause gives a clear when-to-use context. It stops short of naming alternatives or explicit when-not-to-use conditions (e.g., vs. privacy_check), so it is clear context without routing.

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