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

Annotations (readOnly, non-destructive, openWorld) are consistent and the description adds substantial behavioral detail beyond them: dual detection strategy, the guarantee that fixed patterns can only raise the verdict, classifier-resistance to manipulation, the quoted-text exemption, and the 20,000-char limit. It also discloses the payment model and per-call price, which the annotations do not cover.

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?

Long but dense and front-loaded: purpose first, then return shape, then mechanism and caveats, then pricing. Almost every clause carries information, though the pricing/x402 sentence could be trimmed for a single-purpose detector.

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?

There is no output schema, so the description correctly takes on the burden of describing return values (verdict enum values, risk score range, techniques with quoted evidence, advice). It also supplies the critical commercial detail (price and x402 payment path) and a runnable example input, leaving no gap an agent would need filled before calling.

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 both parameters are already documented in the schema, so the baseline is 3. The description largely restates the schema (20,000-char limit, optional context 'what your agent is doing') rather than adding syntax, format, or defaults beyond it.

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 detection', 'check untrusted text') and defines scope (web page, email, tool result, user message). The description enumerates exactly what the tool returns (verdict, 0-100 risk score, techniques, quotes, advice), making its function unmistakable.

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?

Gives clear usage context: check untrusted text 'before your agent reads it', with concrete input types listed. It also carves out an important exclusion (quoted examples in articles are not attacks). It stops short of naming or contrasting the closest sibling, scam_message_check, to disambiguate which one to call.

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