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

Goes well beyond the annotations, which only cover safety (readOnly/idempotent/non-destructive). It discloses detection mechanics (RE2 with re-checking, Luhn, mod-97), format caveats (national phone formats need + code), latency (<1s), price, free-tier limit, and a no-logging guarantee.

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?

Front-loads purpose and the routing to the sibling in the first two sentences; the rest is dense but each clause carries operational value (limits, caveats, docs). Slightly packed, with pricing/docs link tacked onto the tail.

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?

An output schema exists, yet the description still summarizes the return shape (masked text plus per-entity type, offsets, replacement, counts). Combined with detection exclusions, format caveats, and limits, an agent has everything needed to invoke 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?

Schema coverage is 100%, so the schema already documents all three parameters. The description still adds practical meaning, notably the phone-format constraint on 'phone' detection and how mask modes affect output, going modestly beyond the schema text.

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+resource ('Redact PII from text') and enumerates exactly which entity types are handled (emails, phones, cards, IBANs, SSNs, IPs, crypto). It also names the sibling that handles the adjacent task, so it is distinguishable without opening a schema.

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 routes the agent: 'For API keys and tokens use check_text_for_secrets.' It also gives when-not guidance by listing what is left alone (prices, dates, order numbers) and what is not detected (person names, street addresses).

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