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

Beyond the annotations (readOnly, idempotent, openWorld, non-destructive), it discloses two things the structured fields cannot: a hard free quota of 10 calls per day, and the exact failure mode past that (returns the x402 pay-per-call endpoint and price rather than an error). It also names the three verdict values returned per address, so the agent knows the shape of a successful response without an output schema.

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?

Three sentences with zero filler: purpose and covered signals first, capacity and return values second, commercial terms last. Each sentence carries distinct information an agent needs before calling.

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?

For a batched read-only screening tool with no output schema, nothing material is missing: batch limits, supported chains, verdict vocabulary, and the rate-limit/fallback behavior are all stated. The agent can decide whether to call and predict the response without opening the schema.

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 chain enum and address formats are already fully documented in the schema. The description's "1-100 EVM or Solana addresses per call" restates maxItems/minItems and the address field description rather than adding new meaning, 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?

The description gives a specific verb and resource ("Screen counterparty addresses") and enumerates exactly what is checked: OFAC sanctions, scam/phishing wallets, labeled protocol contracts, and brand-new-address detection. It stops short of naming its nearest siblings (wallet_safety, risk_batch, approval_scan), so an agent must infer the boundary, which keeps it below a 5.

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?

It states the decision points that should trigger the call ("before sending, approving, or interacting"), which is genuinely actionable context rather than a restatement of the name. It offers no explicit when-not-to-use and points to no alternative tool, so the exclusion half of the guidance is missing.

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