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

Annotations only cover the read-only/safe profile, but the description adds material behavior: per-call pricing ($0.009 USDC via x402), accepted payment chains, auto-payment behavior for x402 clients, and a grading rule ('Young or illiquid tokens can never grade above C'). Payment and grading constraints are exactly the kind of context annotations cannot express.

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 result shape are front-loaded and the length is defensible for a tool with payment semantics, an unusual grading rule, and no output schema. It is somewhat dense/run-on with minor repetition (mint/freeze/owner powers restated), but no sentence is truly wasted.

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?

With no output schema, the description carries the return-value burden and does so fully: grade, label, score, reason, share_url, share_text, and key facts. Combined with supported chains, parameter aliases, pricing, and a runnable example, an agent has everything needed to call it correctly.

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 67% (both token fields documented, chain not). The description adds value beyond the schema by noting 'solana auto-detected' and confirming the tokenAddress alias, plus the accepted address formats. The chain default is already in the schema, so this is a modest increment rather than full compensation.

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 opening states a specific verb and resource: 'Instant buy-or-avoid verdict for a token,' and then concretely enumerates what comes back (grade A-F, label, 0-100 score, reason, shareable page). It also names every supported chain and both input forms, so an agent understands exactly what this produces versus generic siblings like token_security.

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?

Context for use is clear (a fast pass/fail risk call before buying) and the free-sample example shows exactly how to invoke it. However, it never names or contrasts the many competing siblings (token_security, token_precheck, token_simulate, token_ai_verdict), so the agent is left to infer when to prefer this over them.

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