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

Annotations already cover read-only/idempotent/non-destructive, and the description still adds substantial behavioral context beyond them: deterministic rules with no LLM, batch ceiling of 100 texts, cost of $0.002 USDC per call charged only on success, and what happens without an x402 wallet. It also discloses the full return payload (verdict, action, score, findings with spans, decoded payloads, sanitized copy), which is a lot of load-bearing detail for a no-output-schema tool.

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 lead clause front-loads the purpose and the use context, and the remaining length is spent on concrete detection categories rather than filler. The long enumeration of threat classes is dense but each item carries information; it could be broken into a list for readability but nothing is genuinely wasteful.

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 takes on responsibility for describing returns, and it does so thoroughly — verdict values, action values, score range, findings with character spans, risky links, decoded payloads, sanitized copy. Combined with the pricing and wallet fallback behavior, an agent has everything needed to decide whether to call and how to interpret the result.

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%, so `text`, `items`, `source`, and `sanitize` are all already documented, and the enum tuning note lives in the schema itself. The description adds only the batch ceiling ('up to 100 texts per call'), which is already in the schema as maxItems, so it stays at the baseline 3 rather than earning more.

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 description states a precise verb and resource (scan text for prompt injection) and enumerates the exact threat classes covered, so an agent knows exactly what the tool does. It does not explicitly contrast itself with the sibling `preview_scan_text`, so the only thing separating free preview from this paid call is the cost sentence, which requires inference.

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?

It gives a clear trigger condition — text your agent is about to read — with concrete examples (tool output, web page, email, document, token metadata). It never names an alternative tool such as `preview_scan_text` or `list_rules`, and offers no when-not-to-use guidance, so the alternative-selection half of the dimension is missing.

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