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

Annotations already establish read-only, idempotent, non-destructive and closed-world behavior. The description adds genuinely new information beyond them: the shape of the output (risk level, score, reasons, recommended actions) and the privacy guarantee that the message is not stored or transmitted.

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-loaded with the action and target, and every element (pattern list, languages, outputs, privacy) carries information. The long parenthetical pattern list is dense but earns its space; no filler sentences.

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, the description must summarize returns, and it does so (risk level, score, reasons, immediate and follow-up actions). Parameters are fully covered by the schema, so nothing an agent needs to call this 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 description coverage is 100%, so the schema already documents all three parameters, including the hxxp/[.] link obfuscation convention. The description adds no meaning about unknownSender or repeatedContact or how they alter scoring, so it sits at the baseline.

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?

Names a specific verb (score) and resource (text, email, chat or voicemail transcript) and enumerates the scam-pattern families checked, including supported languages. An agent can tell this apart from the sibling link_check without opening either 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?

The context for use is clear: screen a received message for scam risk. However, it never states when NOT to use it or routes the agent to link_check for URL-only inspection, even though 'disguised links' is one of the listed patterns — that overlap is left to inference.

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