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

Annotations already declare readOnlyHint and openWorldHint, so the safety profile is covered; the description adds the truncation/size limits, the single-page URL restriction, and the exact response contents (verdict, score, top 3 findings). It does not say how a failed fetch or mixed text+url input is handled, leaving a small behavioral gap.

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 capability and its limits are front-loaded in one dense sentence, and the follow-up instruction is kept to a short trailing line. The trailing line is telegraphic ('After: input_guard for every finding and the cleaned text') and slightly harder to parse than the rest.

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 two-parameter tool with no output schema and thin annotations, the description covers input constraints, detection scope, and return values, which is most of what an agent needs. Remaining gaps are edge behavior: what happens on fetch failure, with both inputs present, or when text exceeds 4,000 characters.

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 0%, so the description carries the burden and largely meets it: 'up to 4,000 characters of text, or one https page' explains both parameters and their constraints, and the 'or' signals mutual exclusivity that the schema does not encode. It still does not specify precedence or behavior when both or neither parameter is supplied.

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 ('prompt-injection quick scan for untrusted input') along with scope limits (4,000 characters or one https page), the detection classes (role override, invisible Unicode, hidden HTML), language coverage, and the return shape. It is clearly distinguishable from the sibling 'input_guard', which it names as the follow-up full 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 'After: input_guard for every finding and the cleaned text' line gives an explicit two-step workflow and identifies the alternative sibling. It does not state when to skip the preview (e.g., batch or oversized payloads), so the guidance is clear but not complete on exclusions.

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