scam_message_check

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

No annotations exist, so the description carries the full burden and does so richly: it discloses the returned fields (verdict, risk score, scam type, red flags, advice), the detection mechanisms (RDAP domain age, 40-brand look-alike detection, punycode, Tron on-chain activation checks), a security-relevant invariant ('fixed checks can only raise the verdict' – anti prompt-injection), plus cost ($0.003 USDC), latency (p99 6000ms) and the underlying model.

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 use case are front-loaded and most sentences earn their place by conveying return shape, mechanisms, and operational constraints. It is dense and runs long with a few illustrative asides (specific look-alike domains, model name) that border on surplus but do not obscure the core.

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 and no annotations, the description fully compensates: it enumerates return values, input limits, detection behavior, cost, and latency. An agent has everything needed to decide to call it and to 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 description coverage is 100%, so the schema already documents all three parameters with types and max lengths. The description only echoes 'Up to 8,000 characters; optional sender and channel' without adding format, syntax, or semantic detail beyond the schema, so the baseline 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 verb and resource ('Scam and phishing detection... check a DM, cast, tweet, email or comment') and names the consumer (crypto wallets, trading bots, social agents). It is clearly distinguishable from nearby siblings like prompt_injection_check or token_security without opening any 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 explicit context and timing ('check ... before your agent or user acts on it') and enumerates the message sources it covers. It does not name an alternative tool or state when NOT to use this one, so it falls short of full routing guidance.

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