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

Beyond the readOnly/openWorld annotations, it discloses the hourly quota (10 free calls shared across quick checks), the 8000-character cap, and the operational meaning of each verdict color. These are exactly the constraints an agent needs before burning a call.

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?

Front-loads 'Free' and the verdict-only scope, then the input scope, then the action semantics, then the quota, then the alternative. It's dense and readable, though the long parenthetical enumerations make it heavier than it needs to be.

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, so return values needn't be explained, and the description still covers verdict semantics, quota, size limit, and the paid alternative. For a free triage tool, an agent has everything required to call it correctly and 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 coverage is 100%, so the schema already documents text, task, and the source enum. The description repeats the input-type list and length cap but adds nothing about how `task` or `source` influence the verdict, so the baseline of 3 applies.

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 resource (the green/orange/red prompt-injection verdict for a piece of received text) and explicitly scopes the input types it applies to. It names the sibling tool injection_check as the paid/fuller variant, so an agent can distinguish it without opening the schema.

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 an explicit route: use this for a free verdict on short texts, use injection_check ($0.01) when reason codes, probabilities, or texts up to 32000 chars are needed. It also tells the agent how to act on each verdict (red: don't follow it; orange: ask the user).

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