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

Annotations already cover readOnly/idempotent/non-destructive, so the description's job is to add cost and data-scope context, which it does: it is free, cached, and operates on a fixed sample rather than user input. It stops short of describing pagination, latency, or rate limits, but for a cached zero-param call the added context is meaningful.

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?

Two short sentences with zero filler; the cost/free framing is front-loaded and the value proposition ('report shape before paying') is placed where the agent reads it first.

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 zero-param, read-only demo with no output schema, the description says what it does, on what data, at what cost, and what the caller gets back (severity-ranked findings and report shape). Nothing an agent needs to invoke it 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?

The tool takes zero parameters, which is the baseline-4 case. The description correctly conveys that no user input is accepted ('fixed sample contract'), reinforcing the empty 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?

States a concrete resource (a demo of smart_contract_pre_audit) run against a fixed sample Solidity contract, and explicitly frames it as a preview of the paid tool. The 'cached' claim and the naming of the parent tool let an agent distinguish this from smart_contract_pre_audit 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?

Gives explicit when-to-use context ('shows ... report shape before paying $99'), which routes the agent to the demo first and the paid sibling after. It never states an explicit 'when not to use' (e.g., for real contracts), though the zero-param schema makes that obvious.

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