token_security

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

With no annotations supplied, the description carries full behavioral burden and does so well: it discloses the $0.009 USDC per-call cost, p99 latency of 8000ms, that computation is done directly on-chain, the possible verdict values including the 'incomplete' failure mode when trade simulation cannot run, and the concrete category of flags returned. This is unusually complete behavioral disclosure.

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?

The purpose and cost/latency are front-loaded, which is good, but the body is a single wall of run-on, semicolon-filled sentences listing dozens of individual flags. Much of that flag enumeration could be trimmed without losing routing value, so it is dense and informative but not tightly structured.

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 complex, annotation-free tool with no output schema, the description supplies a strong picture: what it returns, the cost/latency, supported chains and token standards, and detection categories. It stops short of full completeness only because the description's chain list and the enum disagree on avalanche/optimism, and no return-shape detail is given.

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 coverage is only 50% (the chain enum has no schema description), so the description must compensate. It documents the token param's dual form (EVM 0x address or Solana mint, required) and adds genuinely new meaning by stating that a base58 mint is auto-detected as Solana, plus it notes base as the default chain. Minor gap: the param list omits avalanche and optimism even though the enum includes them.

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 states a specific verb+resource (token security / honeypot check with an A-F risk grade) and scopes it precisely to pre-buy due diligence across named chains. It is clear what the tool produces (verdict, summary, flags), but it never differentiates itself from close siblings like token_verdict, token_precheck, or token_ai_verdict, so an agent cannot tell them apart from the text alone.

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?

"Before buying or accepting it" gives an implied use case, which is more than nothing. However, with four or five similar token-evaluation siblings present, the description offers no explicit when-to-use-vs-alternative routing, no exclusions, and no prerequisite guidance, leaving the agent to infer.

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