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

Annotations already cover the safety profile (readOnlyHint, closed-world), and the description adds genuinely new behavioral facts: the credit cost per successful call and that schema-invalid input is rejected before billing. It does not discuss detection rules, determinism, or latency, so it stops short of a 5.

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?

Two dense sentences, front-loaded with purpose and the cost term last. The inline JSON return signature is slightly clunky in prose form, but it earns its space because no output schema exists.

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 spelling out the return shape (risk, score, hits with rule/weight/match/index) and the billing model. Minor gaps remain around what the risk thresholds mean in practice and which rule families are covered.

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?

The single parameter is fully documented in the schema (100% coverage), so the baseline is high. The description adds value by giving concrete examples of what counts as 'untrusted text' (web pages, emails, tool output), which the schema's terse 'Untrusted text' does not convey.

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 (scans), a specific resource (untrusted text: web pages, emails, tool output), and a specific target (prompt-injection patterns), plus what it returns. It is clearly distinguished from the neighbouring prompt-lint tool, which implies linting prompts you author rather than scanning third-party content.

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 phrase 'before it reaches your agent' gives clear situational context for when to call it. However, it never names an alternative (e.g. prompt-lint) or states when not to use it, so the agent must infer the boundary itself.

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