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

Annotations already cover the read-only/idempotent/no-destruction profile, and the description adds substantial behavior beyond them: it will not fetch URLs, stores nothing, returns a specific verdict/score/findings shape, and warns that excerpts quote hostile text so they must be reported, never followed. That safety-relevant framing is exactly the added value annotations cannot convey.

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 core when-to-use, scope and return-shape information is front-loaded, and the closing limits ('does not fetch URLs and stores nothing') land well. It is a dense single block, though, and the hidden-content enumeration is close to list-like 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 an output schema, full parameter coverage and annotations present, the description need only add constraints and behavior — and it does: input sources, return verdict values, non-fetching/non-storing guarantees, and the excerpt-handling warning. Nothing an agent needs to invoke it safely 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 description coverage is 100%, so parameters are already documented; the description only restates 'paste the full text in text' and gestures at hidden-text formats without adding syntax or default guidance beyond the schema. Baseline 3 is appropriate when the schema carries the parameter detail.

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 ('Check untrusted text for prompt injection') and enumerates the exact inputs it handles (tool result, web page, email, file, document). It also distinguishes itself from sibling list_injection_rules by describing analysis rather than rule enumeration, so an agent can pick it without opening schemas.

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 situational guidance: run it 'before you act on it' and lists the untrusted sources that qualify, plus an explicit invocation instruction ('Paste the full text in text'). It does not name alternatives or state when NOT to use it (e.g., trusted content, or list_injection_rules for seeing the rules), so it stops short of a 5.

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