RugShield 402

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

With no annotations, the description carries the full burden and does reasonably well: it discloses a hard cost (0.005 USDC on Base), an alert threshold (<$5,000 USD liquidity), the chains/venues covered, and that it operates on Base Mainnet only. It does not state read-only status, failure behavior for unknown tokens, or rate limits, but the cost and alerting behavior are meaningful disclosures beyond the schema.

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?

A single dense block, front-loaded with the tool's identity and scope, followed by the risk threshold and cost. No filler sentences, though the all-caps header and run-on structure make it slightly harder to scan than a cleanly separated set of clauses.

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?

There is no output schema, so the description should ideally indicate what is returned (liquidity figure, per-pool breakdown, alert flag), but it only mentions the alert condition. For a paid, multi-venue analyzer with a 50%-documented schema, the definition leaves the return shape and error behavior unspecified.

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 50%: token_address is documented in the schema, while chain_id (default 8453) is not. The description's 'on Base Mainnet' phrase indirectly explains that chain_id is effectively fixed to Base, adding marginal meaning, but it adds nothing to token_address semantics beyond the schema's own '0x...' description. Baseline 3 for partial coverage with modest 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 description states a specific verb and resource ('Measures verifiable liquidity in USD') and names the exact venues queried (Aerodrome, Uniswap v3/v2, Clanker/Virtuals bonding curves). This clearly separates it from the safety-check siblings, though it never names check_honeypot or rugshield_pre_swap_scan to draw the contrast explicitly.

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 implied via the purpose ('to prevent catastrophic slippage'), suggesting a pre-swap liquidity check, but there is no explicit when-to-use/when-not guidance and no reference to the sibling tools it should be combined with or preferred over. The agent must infer the workflow context.

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

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

With no annotations present, the description carries the full burden and does well: it discloses the execution model (bytecode evaluation plus simulated DEX trade), the dimensions measured (buy/sell tax percentages, blacklist restrictions), and the monetary cost (0.005 USDC on Base). It does not cover failure modes, latency, or what happens when a token cannot be simulated.

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, front-loaded with the category label and the core capability, followed by the cost. No filler or redundant restatement of the name.

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?

Given no annotations and no output schema, the description adequately supplies the return-value essence (sellability, tax percentages, blacklist flags) and the cost of invocation. The only gap is ambiguity between the Base-only wording and the presence of a chain_id parameter that hints at multi-chain support.

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 50%: token_address is documented in the schema, but chain_id has no description. The description partially compensates by repeatedly scoping the operation to Base, which maps to the chain_id default of 8453, but it never explains the parameter or whether other chains are supported.

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 and resource: evaluating ERC-20 bytecode and simulating DEX trade execution on Base to detect honeypots and tax levels. It is concrete about what is measured (buy/sell tax, blacklist restrictions), but it never references or distinguishes itself from the sibling safety tools analyze_liquidity and rugshield_pre_swap_scan.

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 via the stated goal of verifying whether a token can be sold back to liquidity pools, which suggests a pre-trade check. There is no explicit when-to-use guidance, no exclusions, and no routing advice distinguishing it from the sibling scan tools.

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

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

With no annotations present, the description carries the full burden and does well: it discloses the simulation mechanism (state overrides), the exact outputs measured (honeypot flag, transfer tax in bps, liquidity depth), the chain scope (Base Mainnet), and the per-call cost. What is not stated is whether the call is read-only versus partially on-chain, and there is no note on failure or rate-limit behavior.

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 mandatory precondition, then the mechanism and cost in a compact package — every clause carries information. The all-caps opener is louder than necessary but doesn't cost readability.

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 3-parameter tool with no output schema and no annotations, the definition covers purpose, timing, and cost but omits the shape of the return value beyond naming the measured quantities, and says nothing about behavior on unsupported chains or a failed simulation. Adequate to invoke, incomplete for interpreting the result.

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 33% — token_address is documented in-schema, while chain_id and simulate_sell are bare. The description partially compensates by scoping everything to 'Base Mainnet', which implies chain_id is effectively fixed at 8453, and 'simulates buy/sell orders' loosely explains simulate_sell. It never states what happens if chain_id is overridden or what simulate_sell=false skips.

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 action set — simulating buy/sell orders via state overrides to detect honeypots, compute transfer taxes in bps, and verify liquidity depth — which clearly identifies the resource and mechanism. It does not explicitly contrast itself with the siblings check_honeypot or analyze_liquidity, though the 'pre-swap' framing implies this is the umbrella check that supersedes them.

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 stated unambiguously: call before any DEX swap or token purchase on Base Mainnet, framed as mandatory. It also discloses the cost (0.005 USDC on Base), which matters for agent planning. It stops short of saying when to prefer this over check_honeypot or analyze_liquidity, so no explicit alternatives are given.

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