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

Beyond the annotations (readOnlyHint/openWorldHint), the description discloses pricing ($5 USDC per call via x402), expected latency (30-120 s), async behaviour, and a concrete failure mode ('unverified contracts are refused and not charged'). It also spells out the return payload (findings with severity/file/function/fix, centralisation summary, security score, PDF), which is exactly the behavioural context an agent needs before committing to a paid call.

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?

It is a dense, single-paragraph block, but it is front-loaded with the core purpose and each clause carries new information (checks, outputs, cost, latency, refusal rule). The mid-sentence enumeration is long yet earns its place; nothing is pure filler.

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 shape, the PDF artifact, the cost, the runtime, the async path and the refusal case. For a paid, potentially slow, multi-chain audit tool, an agent has everything needed to decide and call.

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 80%, so the schema already documents pdf, async, chain and webhook_url, and the description largely restates them (chain list, 'async=true supported', PDF output). It adds the async job-id semantics implied by 'async=true supported' but gives no extra guidance on webhook usage, pdf=false behaviour, or address format, so it stays at the baseline for a well-covered schema.

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 names a specific verb and resource (AI smart-contract security audit of verified contracts), enumerates the exact chains supported and the full checklist of vulnerability classes covered, which is far more concrete than a generic 'inspect' tool. It never names an alternative (e.g. contract_inspect, vulns), so an agent must infer the boundary from scope alone rather than being told it.

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 context is implied rather than stated: the tool is clearly for auditing a verified contract address, and the cost ($5 USDC) plus the 'unverified contracts are refused and not charged' rule give useful selection conditions. However there is no explicit when-to-use/when-not guidance and no routing to sibling tools such as contract_inspect or vulns for cheaper or narrower checks.

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