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

With readOnly/idempotent/openWorld annotations already declared, the description still adds substantial context: output shape (0-100 score, label, evidence spans), an explicit batching ceiling of 50, a disclaimer that results are heuristic rather than verdicts, and the pricing/auth model ($0.002 USDC per successful call via x402 on Solana) plus an alternate HTTPS endpoint. That is well beyond what annotations 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?

One front-loaded paragraph that leads with purpose, then capabilities, then return shape, then constraints/pricing. It is dense and long, but nearly every clause (pattern families, signals, batch cap, price, endpoint) carries information an agent needs; only the long family enumeration is slightly list-heavy.

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?

There is no output schema, and the description compensates by describing the return values (score, label, evidence spans). Combined with pricing, batch limit and the heuristic disclaimer, an agent has enough to invoke it correctly; only the single-vs-batch parameter interaction is left unaddressed.

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% and both parameters are self-documented ('Message to score', 'Batch of messages'). The description only restates the batch limit already encoded as maxItems 50 and leaves a real semantic gap: both parameters are optional and it does not say which takes precedence or what happens if both are supplied.

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+resource ('scam / fraud likelihood for messages, DMs, emails, posts and listings') and enumerates the pattern families it detects, which makes it distinguishable from the many other scanners in the sibling list (phishing_score, prompt_injection_scan, profanity_filter, sentiment). An agent can tell what it does 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?

Usage is only implied by the input domain (messages/DMs/emails/listings) and the caveat 'Offline heuristics, not a verdict'. It never says when to prefer it over the closely related phishing_score or prompt_injection_scan sibling, nor does it state exclusions.

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