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

With no annotations, the description carries the full burden and does well: it discloses the paid x402/USDC pricing model ($0.002 per call), the output classification tiers, and the detection surface including invisible Unicode and base64 decoding. It omits whether submitted text is logged/stored, size limits, and latency, which matter for a tool that receives potentially sensitive page or email content.

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?

Purpose and trigger are front-loaded in the first clause, with the detection list and price following. It is a dense run-on sentence, but nearly every listed detection category adds actionable information rather than padding.

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 or annotations, the description still tells the agent what comes back (safe/suspicious/malicious, 0-100 score, evidence) and what it costs, which covers the two biggest unknowns. The remaining gap is the exact relationship between the `text` and `html` inputs.

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 coverage is 0%, so the description must compensate. It clarifies that `text` is the content under inspection and that supplying `html` enables hidden-element scanning ("base64 payloads and (with html) hidden elements"), but it never says whether `html` is a separate full-document input or a supplement to `text`.

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 names a specific verb and resource — prompt injection detection — and enumerates the exact threat classes it catches, so an agent knows precisely what it does. It never names a sibling tool, so it is clear but not explicitly differentiated from neighbors like web_read or web_fetch.

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?

"check text you are about to read (pages, emails, tool output)" gives a concrete triggering context, which is a real usage guideline. There is no when-not-to-use clause (e.g., trusted/own content, already-scanned text), which keeps it from a 5.

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