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

Annotations already cover read-only and open-world, but the description adds material behavior the annotations cannot: the result is flags plus an overall risk level, responses are cached for 60 s (relevant for freshness-sensitive decisions), and the call is paid at $0.020 via x402 in USDC on Base or Solana. What it does not explain is the failure mode when payment is absent or the tx parameter is omitted, which is the main remaining gap.

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?

Front-loaded with the purpose, then a compact enumeration of checks, then return shape, caching, and pricing — each clause carries distinct information. The check list is dense but every item is a real signal an agent would use to interpret the risk level, so little is 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 correctly takes on the burden of describing the return ('flags and an overall risk level'), and it discloses the two things an agent could otherwise stumble on: caching and per-call payment. It falls short only on payment-failure behavior and on how the overall risk level is derived, which matters for a tool whose whole value is a judgment call.

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 100%, so both parameters (mint address, tx as an alternative to the X-Payment-Tx header) are already documented in the schema. The description adds only indirect context by calling this a Solana tool, and says nothing about the payment parameter's role in the x402 flow beyond the price line. Baseline 3 is appropriate.

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 specific verb+resource ('Rug / scam check for a Solana token') and then enumerates exactly which on-chain signals are inspected (mint authority, freeze authority, Token-2022 extensions, top-10 holder share, DEX liquidity, pool age). The 'Solana' qualifier cleanly separates it from the sibling evm_token_risk without the agent needing to open 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?

Usage is only implied — an agent can infer you call this before trusting or trading a token. There is no explicit when-to-use framing, no exclusion such as 'Solana only, use evm_token_risk for EVM chains', and no guidance on what to do when the check is inconclusive. Minimum viable rather than instructive.

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