scan_dangerous_capabilities

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

With no annotations available, the description fully explains the heuristic method (4-byte selector matching), the meaning of results (presence of capability, not actual operation), and the proxy limitation (logic hidden in implementation is reported). It also mentions no API key is needed, giving a complete behavioral picture.

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 efficiently pack purpose, semantics, heuristic, and limitations without filler. Each clause adds value, though slightly dense for a quick read.

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?

Covers what is scanned, specific capabilities, heuristic meaning, proxy limitation, and operational detail (no API key). It does not specify exact output structure, but 'flags presence' is sufficient for a simple single-parameter tool with no output 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?

The schema already describes the single parameter fully ('Contract/token address on Base'), and the description adds no additional format, validation, or usage detail beyond the schema. Baseline of 3 applies due to high schema coverage.

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 clearly states the tool scans deployed bytecode for owner-only powers (mint, pause, blacklist, etc.) using a specific verb and resource. It differentiates from sibling risk/safety tools by focusing specifically on selector-based capability detection, independent of token claims.

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?

Implies usage for verifying a token's actual on-chain capabilities versus its stated claims, but no explicit when-to-use or when-not-to-use guidance is given. It does not reference alternative sibling tools like token_safety_screen, leaving the choice implicit.

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