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

With readOnlyHint=true, idempotentHint=true, and destructiveHint=false already covering the safety profile, the bar is lower; the description earns credit by disclosing the $0.01 USDC x402 cost, a real behavioral side effect annotations cannot express. It also clarifies input format and enumerates exactly what findings are returned. Minor gap: it does not flag that the submitted source code is transmitted to an external service.

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 sentences, roughly 40 words, with zero filler. Input format and findings list are front-loaded, and the cost disclosure earns its place as the closing sentence. Every word adds signal.

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 simple one-required-param tool with annotations covering safety, the input format, cost, and findings categories give an agent enough to invoke it correctly. But with no output schema, the description carries the return-value burden and only lists finding names, not their structure; it also leaves 'filename' unexplained and does not differentiate from demo_audit. Adequate but with real gaps.

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 only 50% (code has 'one JS/TS file', filename has none), so the description should compensate but does not. It merely restates the schema's type for 'code' ('Input one JS/TS source file (string)') and says nothing about 'filename's purpose or when it should be supplied. It adds essentially no meaning beyond the structured 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 (audit), resource (crypto-bot JS/TS source), and enumerates the exact bug categories it detects (testnet-as-USD, silent-zero balance, cooldown key mismatch, fake faucet endpoint, speculative earnings text). The title echoes this. Among a sibling list dominated by chain_* and market_* tools, its purpose is unmistakable, and it is substantially differentiated from the closest sibling, demo_audit.

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 via 'Input one JS/TS source file (string)' and the specific fake-earnings bug list, so an agent can infer when it applies. However, it never states when not to use it, names the alternative (demo_audit exists as a sibling), or gives selection conditions. Clear context, but no exclusions or alternative routing.

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