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

Annotations already cover the safety profile (readOnlyHint, openWorldHint), so the bar is lower, and the description still adds return shape (risk score, findings, sanitized copy), sanitization behavior, and per-call cost (x402 USDC). The pricing is stated inconsistently ($0.004/text, $0.006/URL, then $0.006 per call), which slightly muddies cost expectations, but the behavioral value added is real.

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 purpose and scoped in two sentences with no filler; the threat enumeration is long but materially useful for selection. It is slightly run-on, with the pricing clauses tacked on the end, keeping it from a top score.

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?

With no output schema, the description correctly compensates by describing returns (risk score, findings, sanitized copy). The main residual gap is that all five parameters are optional, yet the description never states that at least one of text/html/url must be provided, which an agent calling blindly would need to know.

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 description coverage is 100% and each parameter is already documented (strip vs flag mode, deep model judgment, hidden-element inspection). The description restates the accepted input types (text/HTML/URL) but adds no format, precedence, or combination guidance (e.g. whether exactly one input should be supplied). Baseline 3 applies when the schema carries the semantics.

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 with clear scope: inspect untrusted text/HTML/URL for prompt injection before a model reads it. It enumerates concrete detection targets (hidden text, invisible Unicode/ASCII smuggling, role spoofing, exfiltration, payment hijacks, tool-call injection), which distinguishes it from generic moderation or redaction tools. An agent can tell what it does without opening the 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 trigger condition is explicit and actionable: use it on untrusted content 'before your model reads it.' However, it names no alternatives or exclusions, so a sibling like moderate/moderations or pii_redact is never explicitly ruled out as the better choice. Clear context, but no routing guidance.

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