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

Annotations only supply readOnlyHint and openWorldHint; the description goes well beyond them by disclosing the billing model ($0.002 USDC per successful call via x402 on Base/Solana/Arc, failures not charged), the return shape (redacted text plus counts), and detection blind spots. This is exactly the kind of context annotations cannot carry. It stops at 4 because it says nothing about determinism, truncation, or how counts are defined.

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-loaded with the action, then the coverage list, then limitations, then price — a sensible order with no filler sentences. The pattern enumeration is dense but each item earns its place by telling the agent what will and won't be caught; a minor deduction for cramming everything into one long sentence run.

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 low-complexity single-input transform, the description covers the action, the detection scope, the known failure modes, the cost, and the return surface, and an output schema exists to document the response. An agent has everything needed to decide whether to call it and what to expect.

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?

There is a single parameter with 100% schema description coverage, including the 1–50,000 character bound, so the schema already carries the semantics. The description adds no format, encoding, or batching guidance for the input text, which is the expected baseline-3 outcome for a one-param tool.

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 ('Masks likely secrets and personal data in agent logs or chat text') and then enumerates the exact pattern classes covered (0x private keys, JWTs, AWS key ids, sk-/ghp_/xoxb- tokens, Luhn-valid card numbers, emails). This is precise enough to separate it from nearby siblings such as prompt_injection_firewall or scam_phishing_message_filter without opening any 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?

The description scopes usage to 'agent logs or chat text' and discloses the boundary conditions that matter for deciding to rely on it ('pattern-based: it can miss unusual formats and does not detect seed phrases or names'). It does not name an alternative sibling or spell out a when-not-to-use rule, so it stops short of full routing guidance.

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