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

Beyond the readOnly/idempotent/non-destructive annotations, it discloses the three return classifications, the 4,000-char input cap, the matched-rule categories, and — critically — the per-call cost and payment rails (x402, USDC on five chains). Cost and billing model are behavioral facts annotations cannot express.

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?

Three sentences, front-loaded with the usage trigger, then return semantics, then cost. Every clause adds decision-relevant information with no filler.

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?

An output schema exists, yet the description still summarizes the verdict taxonomy, and it adds the cost dimension an agent must budget for. Nothing needed to call this single-parameter, read-only tool correctly is missing.

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 100% for the single 'text' parameter, and the description's only parameter detail (the 4,000-character limit) merely restates the schema. Baseline 3 applies since the schema already does the documentation work.

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 (screened) and resource (untrusted text for prompt-injection attempts) with clear scope. It is trivially distinguishable from siblings like get_sanctions_check or get_honeypot_check, which screen different artifacts.

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 opening 'Use when an agent needs untrusted text screened for prompt-injection attempts' gives a concrete trigger condition. It does not name when-not-to-use or an alternative sibling, but no sibling overlaps enough to require exclusion.

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