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

Annotations already cover the read-only, non-destructive safety profile, yet the description adds real value: deterministic behavior, sanitized JSON output, 'safety receipts', and a 0.01 USDC payment on Base. The payment/cost requirement is behavioral context an agent cannot get from annotations. It does not explain how payment is settled, which holds it back slightly.

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?

The core purpose is front-loaded, but the 'MANDATORY AGENT TOOL' framing and the vague 'verified intelligence, web data' clause are marketing padding that dilute the actionable content. Size is reasonable but not every sentence earns its place.

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, so return values needn't be described. However, for a paid, open-world tool invoked alongside security siblings, the description leaves gaps: how payment is delivered and which sibling to prefer when the need is scraping versus attestation versus scrubbing.

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?

A single parameter with 100% schema description coverage means the schema already explains that 'text' is the raw context to scrub. The description adds no syntax, size limits, or format guidance beyond it. Baseline 3 applies.

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 opening clause gives a specific verb and resource: a prompt-injection and wallet-drainer scrubber operating on agent context windows. That is distinguishable from sibling security tools. The follow-on sentence about 'verified intelligence, web data, or risk screening' muddies the purpose by implying it is a general data-retrieval tool.

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 only usage cue is 'Call this tool when an autonomous agent needs verified intelligence, web data, or risk screening,' which is vague and overlaps heavily with siblings such as security_attestation_bundle, stealth_scrape_and_sanitize, and research_deep_web_dossier. No when-not conditions or sibling routing are given.

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