tech-risk

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

With no annotations, the description covers key behavioral aspects: network (Base mainnet), inclusion of USD price, multi-provider JSON-RPC, and cost per call. Missing details like error handling or rate limits, but sufficient for a simple read operation.

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 description is two sentences, front-loading the core function, then adding cost info. Every sentence adds value with no redundancy.

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 the simplicity (one param, no output schema), the description covers the main purpose, network, and cost. It could specify return units (e.g., wei vs ETH) for completeness, but overall is adequate.

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 input schema has 100% coverage for the single parameter 'address', which is described as a '0x-prefixed 20-byte Base address'. The tool description adds no further meaning, so 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?

The description clearly states it returns 'Native ETH balance of a Base mainnet address, incl. balance_usd', which is specific and distinguishes from sibling tools like chain_token_balance.

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?

The description mentions cost and multi-provider usage but does not explicitly guide when to use vs alternatives (e.g., chain_token_balance) or provide when-not-to-use scenarios.

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?

Discloses multi-provider failover, never fails on rate limit, and cost per call. Full behavioral disclosure given no annotations.

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 concise sentences that front-load the key purpose and behavior with no wasted words.

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?

Does not describe the return value (e.g., numeric block number), but given the tool's simplicity, this is a minor gap.

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?

No parameters exist; schema coverage is 100%. Description need not add parameter info, baseline 4 applies.

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?

Explicitly states it returns the current block number on Base mainnet via multi-provider JSON-RPC, clearly distinguishing from siblings like chain_block_number_preview.

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?

Describes the scenario (getting current block number) and mentions failover behavior, but does not explicitly state when not to use it or provide alternatives.

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 provided, the description carries the full burden. It discloses that the data is a free sample and identical to the paid version, but lacks details on rate limits, latency, or response format. Basic behavioral context is given.

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, front-loaded sentence that conveys all essential information with no wasted words. It is optimally concise for its purpose.

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 simple tool with no parameters and no output schema, the description covers the core purpose and relationship to the paid sibling. However, it does not specify the return value format, which could cause uncertainty for an agent.

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 tool has zero parameters, so the description adds no parameter info. Per guidelines, baseline is 4 for 0 params. The schema already covers everything, and the description does not detract.

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 explicitly states the tool provides a free live sample of the current Base mainnet block number, identical to the paid chain_block_number tool. This clearly distinguishes it from siblings and specifies the resource and verb.

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?

The description mentions it is free and identical to the paid tool, implying its use for cost-free testing or sampling. However, it does not explicitly state when not to use it or provide alternative scenarios.

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?

No annotations are provided, so the description carries full burden. It discloses the cost ($0.005 USDC per call) and data source (multi-provider JSON-RPC), but does not mention idempotency, rate limits, or caching 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?

Two sentences with no wasted words. Key information (outputs, cost, data source) is front-loaded.

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?

While the tool has no parameters and no output schema, the description does not specify the exact JSON response structure, which could help an agent parse the result 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?

With zero parameters and 100% schema coverage, baseline is 4. The description adds meaning by detailing the output fields (wei/gwei, base_fee_gwei, priority_fee_gwei, gas_price_usd) and the cross-call mechanism.

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 specifies the tool retrieves current Base mainnet gas prices in multiple units (wei/gwei, EIP-1559 fees, USD price) via multi-provider JSON-RPC, distinguishing it from preview tools.

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?

The description mentions cost and differentiation from ETH-only competitors, but does not explicitly state when to use this tool versus alternatives like chain_gas_price_preview or other gas price 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 provided, the description carries the full burden. It states the tool returns 'identical data to the paid chain_gas_price tool', which is transparent about the output quality. It also clarifies the free nature. Missing details like rate limits or call constraints, but the simplicity of the tool (0 params) reduces the need. A minor gap prevents a 5.

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 description is extremely concise with two sentences, front-loaded with 'FREE live sample' to immediately convey key information. Every word serves a purpose without redundancy or filler.

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 the tool has no parameters, no output schema, and a straightforward function (return gas price), the description fully satisfies contextual needs. It explains what the tool does, how it relates to the paid sibling, and its cost model. No missing information for an agent to select and invoke 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?

The tool has zero parameters, so the baseline is 4. The description does not add parameter information, which is entirely appropriate since no parameters exist. No additional value needed beyond the 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 provides a 'live sample of the current Base mainnet gas price' with the verb 'sample', specifying the resource (gas price) and network (Base mainnet). It distinguishes itself from the sibling 'chain_gas_price' by highlighting it's free and a preview, making the purpose unambiguous.

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?

The description explicitly says 'FREE live sample' and 'No payment required', and mentions the paid counterpart 'chain_gas_price', which implies when to use this preview version. However, it does not explicitly state when not to use it or provide alternative scenarios, so it falls short of a 5.

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, the description provides cost ($0.005 per call), caching per token contract, and the inclusion of symbol/decimals/formatted balance. It does not cover failure modes but is transparent about significant behaviors.

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 with no wasted words. The first sentence front-loads the core purpose and key features (network, return fields, caching), and the second states cost. Every piece of information earns its place.

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 the tool's simplicity (2 params, no output schema), the description covers main purpose, cost, and caching. It hints at return format. Missing edge case behavior (e.g., invalid address) but acceptable for this complexity.

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 100% and parameter descriptions are already clear. The description reinforces the ERC-20 context and adds return field information but does not add significant semantic detail beyond the schema.

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 it retrieves the ERC-20 token balance for a Base mainnet address, including symbol, decimals, and formatted balance. This distinguishes it from siblings like chain_balance which returns native balance.

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?

The description specifies the network (Base mainnet) and mentions the cost, but does not explicitly contrast with siblings or provide when-not-to-use guidance. However, the context of ERC-20 tokens is implicit differentiation.

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 the description carries the full burden, and it delivers unusually rich context: the exact output shape (SAFE | CAUTION | AVOID, risk_score 0-100, reasons), the specific checks performed, and a concrete cost model ($0.005 USDC via the shared MCP payment gate vs $0.01 direct HTTP). It implies a read-only analysis operation without stating it explicitly, which is the only 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 and verdict semantics, and every clause carries information. The pricing sentence is slightly long and partly repeats the cost concept, but the density is justified for a tool with no annotations and no output schema.

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 and no annotations, the description compensates by naming the return fields (verdict, risk_score, reasons) and the underlying checks, plus cost/payment behavior. An agent has enough to decide and invoke 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?

One parameter at 100% schema description coverage, so the schema already defines 'token' as a 0x-prefixed 20-byte Base mainnet ERC-20 address. The description adds only the 'Base ERC-20' framing, which is already in the schema, so baseline 3 applies.

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: a 'token security check (honeypot detector + rug-pull risk score) for a Base ERC-20 in one call,' and enumerates the bundled checks and verdicts. It clearly distinguishes itself from generic RPC tools, but never names or differentiates itself from the very similar MCP siblings chain_token_security and chain_token_report_preview.

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?

'Replaces many RPC calls and prevents a bad trade' implies the use case, and the pricing note helps an agent choose between the MCP gate and the direct HTTP endpoint. However, it gives no explicit when-not-to-use and no routing guidance against the near-duplicate siblings chain_token_security / chain_token_report_preview.

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, the description carries the full burden, and it does disclose the two behaviors that matter most here: zero cost ('No payment required', 'FREE') and output parity with the paid tool ('same depth'). It omits rate limits, caching, or freshness of the data, so it is strong but not complete.

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 front-loaded sentence with the value proposition (FREE) leading and the differentiation from the paid sibling following. No filler.

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?

No output schema and no annotations, so the description must cover scope, cost, and result shape; it covers scope (Base USDC), cost (free), and result shape (SAFE/CAUTION/AVOID verdict, same depth as paid). Only freshness/latency and exact response fields remain unstated, which are minor for a no-param read tool.

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?

Zero-parameter tool, so the baseline is 4. The description compensates usefully by fixing the implicit argument — the report is scoped to Base USDC — telling the agent what it will get without passing anything.

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 and resource ('full real trade-safety report ... verdict') for a specific asset (Base USDC), and explicitly names the sibling paid tool chain_token_report it mirrors. An agent can distinguish it from chain_token_security and chain_token_report without opening a 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?

Makes the selection condition clear: it is the FREE, no-payment-required counterpart to chain_token_report with the same depth, so an agent knows to prefer it when cost matters. It stops short of stating when the paid tool would be required instead.

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?

Describes detailed checks (proxy, bytecode, renouncement, simulation), returns risk_score/verdict/flags, and notes cost. No annotations provided, so description carries burden well. Lacks error handling details.

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?

Packed with information but well-structured: purpose, checks, output, cost. Not overly verbose, each sentence adds value.

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 complexity and no output schema, description covers key aspects: checks, return types, cost. Missing exact output format but sufficient for an agent.

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 100% and description does not add new meaning beyond '0x-prefixed 20-byte ERC-20 contract address on Base mainnet'. Adequate but no extra value.

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?

Clearly states it is a token security/honeypot detector for Base mainnet ERC-20 with specific checks. Distinguishes from sibling 'chain_token_security_preview' by emphasizing real compute and cost.

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?

Mentions cost and that it's non-trivial compute, implying use when serious analysis is needed. Does not explicitly mention when not to use or suggest alternatives like the preview, but provides clear 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?

No annotations are provided, so the description carries the full burden. It mentions it's free and same depth as paid, but does not disclose any behavioral traits like rate limits, data freshness, or what happens if the input is not Base WETH. Minimal transparency.

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 that are efficient and front-loaded with essential information: free, fixed token, same depth as paid, and alternative for arbitrary tokens. No wasted words.

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 parameters, no output schema, and simple functionality of a preview tool, the description is adequate. It explains what it does and how it differs from the paid tool. Could mention that it only works for Base WETH, but that is already clear.

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?

No parameters in the input schema, so baseline is 4. Description does not need to add parameter info. The description correctly indicates no parameters are required.

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?

Clearly states it provides a free full security analysis for a fixed token (Base WETH) using the same depth as the paid tool. Distinguishes itself from sibling 'chain_token_security' by specifying the token is fixed and free.

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?

Explicitly tells when to use this tool (free preview of Base WETH) and when to use the paid tool (arbitrary tokens). Also mentions 'No payment required' and that it's a preview to see the real product before paying.

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?

No annotations are provided, so the description alone must convey behavioral traits. It discloses the cost ($0.005 per call) and the provider mechanism (multi-provider JSON-RPC). However, it does not mention read-only nature, error handling, rate limits, or response format. The cost disclosure is valuable, but other aspects are omitted.

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 description is extremely concise: two sentences, each serving a purpose (what the tool does, and its cost). No filler words. Information is front-loaded with the primary action and resource.

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 should hint at what 'details' means, but it does not. For a single-parameter read tool, this is adequate but leaves the agent uncertain about the returned structure. Cost and chain info are helpful, but completeness is only moderate.

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 input schema covers 100% of parameters with a clear description ('0x-prefixed 32-byte transaction hash'). The description adds no extra meaning beyond the schema, so a baseline score of 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?

The description clearly states the tool retrieves transaction details by hash on Base mainnet, using multi-provider JSON-RPC. This is a specific verb+resource pair, and among sibling tools like chain_balance (balance queries) and chain_block_number (block queries), this tool is distinct.

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?

The description implies usage for transaction hash lookups but does not explicitly state when to use this tool versus alternatives (e.g., preview tools cost less but may have different data). No guidance on when not to use or prerequisites.

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, the description carries the full behavioral burden, and it does disclose two important traits: the call is paid ($0.005 USDC via x402) and the USD value requires a cross-call to an ETH price source. It also flags EIP-7702 delegated-EOA awareness, an edge case that affects the contract check. It does not cover failure modes, latency, or caching.

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?

Purpose and returned fields are front-loaded in the first sentence, with cost isolated in a short second sentence. The parenthetical clauses are dense but each carries real information (cross-call pricing, EIP-7702 awareness) rather than filler.

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?

No output schema exists, so the description must convey return content, and it does by listing the four bundled signals by name. An agent knows what it gets and what it pays. Missing are error behavior and any note on the output shape/units beyond the enumerated fields.

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?

Only one parameter and schema coverage is 100%, so the schema already documents the address format. The description adds the Base mainnet scoping ('for a Base mainnet address'), which slightly narrows the schema's 'Base address' note but is largely redundant. Baseline 3 applies.

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?

Names a specific verb+resource ('Wallet screening bundle') and enumerates exactly what it returns: ETH balance, balance_usd, tx count, and a contract-vs-EOA code check. The 'in one call' framing implicitly separates it from single-purpose siblings such as chain_balance and chain_tx without needing them named.

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?

The bundle framing ('in one call') implies the tool should be chosen when an agent wants all four signals at once, but there is no explicit when-to-use or when-not-to-use statement and no sibling is named as the alternative for single-field lookups. Usage is inferable but not stated.

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, the description carries the full burden and does so well: it discloses exact-match behavior, the two list sources, snapshot dates, returned fields, the meaning and limits of a 'clear' verdict, and the x402 payment cost. This gives an agent the operational context needed to invoke and interpret the tool.

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 description is front-loaded with the core question and screening purpose, then efficiently layers in sources, return values, caveat, and cost. Every sentence earns its place and there is no redundant or vague wording.

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 one-parameter screening tool with no output schema and no annotations, the description supplies the purpose, invocation context, data sources, return semantics, interpretation caveat, and cost. Nothing an agent needs in order to call and understand the result correctly appears to be missing.

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 input schema already documents the single address parameter at 100% coverage, including its 0x-prefixed 20-byte format. The description repeats the counterparty/recipient/spender framing but adds no additional parameter-level meaning beyond the schema.

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 opens with a precise question and then states a specific verb and resource: pre-trade screening a wallet address for sanctions or scam status. It clearly distinguishes this screening operation from general wallet lookup siblings like chain_wallet by focusing on OFAC SDN and threat-intel list matching.

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?

It gives clear when-to-use guidance: before an agent sends, swaps, or approves, for a counterparty, recipient, or token-spender address. It does not explicitly name alternative tools or describe when not to use this one, so it falls short of full explicit when/when-not/alternatives guidance.

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, the description carries the full behavioral burden and does disclose non-obvious traits: per-coin omission of unreachable/non-listing venues, Hyperliquid always present, and an OI-screened set with excluded_thin_venues/oi_weighted flags so thin-book outliers are surfaced rather than silently dropped. It also states the per-call charge, but says nothing about freshness/latency, failure behavior, or what a $0.005 charge failing to settle looks like.

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 core purpose is front-loaded, but the body is one sprawling sentence built around an enormous parenthetical that reads as a raw field dump. Nearly every clause carries real information (there is no output schema), yet the lack of structure makes it hard to scan.

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 compensates by enumerating the returned fields (rates, OI in USD, arb verdict, funding_spread_bps, signals, timestamps, prices, volume) and the screening logic behind the verdict. What is missing is comparatively small: no hint of the paid-call failure mode and no routing to the cheaper preview sibling.

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% and the single `limit` parameter (default 20, max 100) is fully documented in the schema. The description adds no meaning about limit, and in fact never mentions it; baseline 3 applies when the schema does all the work.

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 resource (perpetual-futures funding rates) and a concrete scope (6 named venues, ranked by volume), so an agent knows exactly what data comes back. It never explicitly distinguishes itself from the sibling crypto_funding_preview, leaving that inference to the 'Live' wording and the stated cost.

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?

There is no when-to-use or when-not-to-use guidance; the only decision signal is the appended price line ($0.005 per call). The presence of crypto_funding_preview among siblings makes the missing routing rule ('use preview for a free snapshot') a real gap.

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?

No annotations provided, so description must carry the burden. It discloses that the tool is free and provides only 1 item, but does not explicitly state it's read-only or what behavior to expect. No mention of destructive actions, but none expected.

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 concise sentences with no waste. 'FREE 1-item sample of live cross-venue funding rates. No payment required.' Front-loaded key information.

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 simple tool with no parameters and no output schema, the description is fully adequate. It explains what it does and its free/sample nature. Complete given the tool's simplicity.

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?

Zero parameters with 100% schema coverage (trivially). Description adds no parameter info, but none is needed. Baseline 4 for zero params.

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 it provides a free 1-item sample of live cross-venue funding rates. It distinguishes itself from the full crypto_funding tool by being a preview/sample, and uses specific verb 'sample' and resource 'funding rates'.

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 getting a free sample without payment. The context signals and sibling list suggest crypto_funding is the full version, so the preview is for testing or quick previews. However, no explicit when-not-to-use or alternatives mentioned.

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, the description carries the full burden and does disclose the two things an agent most needs: this is a live/paid call and payment is $0.005 USDC via x402, which implies wallet/auth prerequisites. It does not cover failure behavior (is the charge incurred on error?) or rate limits, which are material for a paid endpoint.

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 resource and return fields, then the cost constraint. Every clause carries information; nothing is padding.

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?

No output schema exists, but the description compensates by listing the return fields (price, change_24h, symbol, confidence, timestamp). For a one-parameter, no-annotation tool the only real gap is error/payment-failure behavior and the explicit pointer to the preview sibling.

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 100% and the single parameter is fully documented there, including comma-separated syntax and the 25-item cap, so the baseline is 3. The description adds little beyond the keying convention ('CoinGecko ids') and is actually slightly narrower than the schema, which also accepts ticker symbols.

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 and resource (live spot token prices) and enumerates the returned fields, so the agent knows exactly what comes back. The source (DefiLlama) and CoinGecko-id keying further sharpen it. It stops short of naming the crypto_prices_preview sibling, so differentiation is implied by the cost line rather than stated.

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?

The cost line ($0.005 USDC per call via x402) implies this is the paid live endpoint and that the free _preview variant exists for sampling, but the description never says so explicitly or gives a when-not condition. The default behavior (top coins, max 25) is only in the schema. Usage is inferable, not guided.

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?

No annotations are provided, so the description bears full responsibility. It discloses the tool provides a free sample of 1 item, which is a key behavioral trait (limited to 1 token). It doesn't mention caching or data freshness, but the core limitation is clear.

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 description is a single sentence of 8 words, very concise. Every word adds value. However, it could be slightly more structured (e.g., listing what is sampled). Still efficient and front-loaded.

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 output schema, the description should explain the return format or what 'live token prices' means. It doesn't specify which tokens are sampled or the output structure. For a tool with no parameters, this is a gap. Partially complete.

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 input schema has zero parameters with 100% coverage, so the description doesn't need to explain parameters. Baseline score of 4 is appropriate; the description adds no param detail but doesn't need to.

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 it provides a 'FREE 1-item sample of live token prices.' The verb 'sample' and object 'token prices' are specific. It distinguishes from the sibling 'crypto_prices' by being a preview/free sample, so purpose is well-defined.

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?

The description explicitly mentions 'FREE' and 'No payment required,' guiding usage for cost-free testing. It doesn't explicitly state when not to use or compare to alternatives, but the preview nature implies it's for exploration. Clear context for usage.

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 supplied, the description must carry the behavioral burden, and it does disclose two material facts: the data source (DefiLlama) and a per-call charge of $0.005 USDC via x402. It says nothing about what happens on payment failure, whether results are cached, rate limits, or pagination depth beyond the limit parameter, which are the practical risks for a paid endpoint.

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 strongest content is front-loaded in the first sentence, but the second sentence is a long comma-chained enumeration of every row field (APY breakdown, il7d, mu/sigma, stability forecast, TVL) that is dense and hard to scan. It is informative rather than wasteful, yet the field laundry list could be trimmed or grouped without losing meaning.

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?

Because there is no output schema, the description correctly shoulders the return-value burden and does so thoroughly — naming the verdict enum, risk_score scale, and the row fields, plus the sort modes and data provenance. What remains thin is payment/error behavior and result pagination, which matters for a paid, list-returning endpoint.

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 100%, so all five parameters are already documented, and the baseline is 3. The description reinforces the sort semantics ('risk-adjusted APY = apy/sigma') and confirms short chain names resolve to DefiLlama canonical names only implicitly through the chain parameter's own description, adding little new meaning. It also refers to passing a 'pool id' that is not a parameter of this tool.

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 opens with a specific resource — live DeFi lending/LP yield pools — and adds the distinguishing feature that every row carries a verdict tag and risk_score, so an agent knows this is a browsing/ranking tool rather than a raw data dump. It also separates itself from yield_entry_verdict by framing that sibling as the deep single-pool check. It never mentions the sibling defi_yields_preview, so the paid-vs-free distinction is left implicit.

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?

Guidance is explicit at the routing point: 'For the deep go/no-go on the one pool you're sizing into, pass its pool id to yield_entry_verdict,' which tells the agent exactly when to leave this tool. The cost line ($0.005 USDC per call via x402) also implies the preview sibling should be used first, but that handoff is never stated outright and no when-not-use conditions are spelled out.

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?

No annotations are provided, so the description carries full burden. It mentions 'FREE' and 'no payment required' which is good, but does not disclose what the sample contains or any limits. For a simple tool with no parameters, it is adequate but not rich.

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 description is extremely concise: two short sentences that convey the essence without any fluff. Every word earns its place.

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 parameters, no output schema, and low complexity, the description sufficiently communicates the tool's purpose as a free preview. It could mention the output format but is largely complete for its scope.

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 tool has no parameters and schema coverage is 100%, so the description has nothing to add. With zero parameters, baseline is 4.

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 it is a free sample of live DeFi yield pools, with the verb 'sample' indicating a preview. This effectively distinguishes it from the sibling tool 'defi_yields' which would provide full data.

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?

The description does not explicitly state when to use this tool versus 'defi_yields', but the word 'preview' in the name and 'sample' in the description imply it is for testing or exploration before using the full version.

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, the description carries the full burden and does well by disclosing concrete behaviors: RDAP lookup, DNS records, subdomain enumeration, certificate transparency, tech fingerprint, and a verdict based on domain age. It also transparently states the cost. Missing details like output format and error handling prevent a perfect score.

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 description is reasonably concise but packs a long list of features into a single dense sentence, followed by a pricing caveat that is somewhat tangential. It is not poorly structured, but the mix of functionality and cost makes it less streamlined.

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?

The description enumerates many enrichment components, giving a good sense of capabilities. However, with no output schema, it does not describe the return structure, and it lacks usage context or relationship to sibling tools, leaving gaps for a complex tool.

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 has one parameter, 'domain', with zero description coverage. The description only repeats 'for a domain' without adding any format, normalization, or constraints, so it fails to clarify the expected input beyond the parameter name.

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 identifies the tool as a comprehensive domain enrichment service, listing specific data sources (RDAP, DNS, subdomain enumeration, CT history, tech-stack) and a verdict. However, it does not explicitly distinguish itself from sibling tool 'enrich_tech_risk', so it stops short of a 5.

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?

No guidance is provided on when to use this tool versus alternatives like enrich_tech_risk. The only comparative instruction is about payment gate versus a direct HTTP endpoint, which is cost guidance rather than usage 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, the description carries the full burden of disclosing behavior. It adds valuable context like the cost ($0.005 USDC per call) and the specific enrichment steps. Yet it does not state read-only nature, side effects, or failure conditions, so transparency is adequate but not thorough.

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 description is two concise sentences, with the core functionality front-loaded and cost neatly appended. Every word earns its place, and there is no fluff.

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?

The description lists the core capabilities and even hints at the output verdict, but with no output schema and no annotations, it lacks details on return structure, parameter prerequisites, and error scenarios. It is minimally viable for an agent to invoke 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 description coverage is 0%, so the description must compensate. It only mentions 'a domain', giving some meaning to the 'domain' parameter, but the 'techstack' array parameter is completely underexplained. This leaves significant ambiguity for the agent.

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 specifies the tool's purpose with a strong verb ('enrich'), a target resource ('a domain'), and distinct outputs (tech-stack fingerprint, CVE mapping, EPSS, CISA KEV, verdict). This effectively distinguishes it from sibling tools like enrich_domain by focusing on technical security risk.

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?

The description provides clear context that this tool is for security/tech-risk enrichment of a domain, implying when it should be used. However, it does not explicitly mention alternative tools or exclusionary conditions, so it stops short of a top score.

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, the description carries the full burden and does well: it discloses the exact cost ($0.005 USDC per call vs. $0.008 on the direct HTTP endpoint), the payment-gate mechanism, and precisely what the response contains. It stops short of stating that the operation is read-only/non-mutating or any latency/rate-limit behavior, which matters for a paid call.

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 decision framing, then returns, then cost — a sensible order. Dense but mostly earns its length because there is no output schema to describe the rich return payload. The parenthetical comparing MCP vs. direct HTTP pricing is slightly redundant detail for a caller who is already using the MCP tool.

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?

No output schema exists, and the description fully compensates by naming the top-level sized_verdict one-liner and each sizing field (entry slippage, exit simulation, round-trip breakeven %, max_safe_notional_usd). Combined with explicit cost and scope (Base mainnet ERC-20), an agent has everything needed to decide and invoke 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 100%, so baseline would be 3; the description earns an increment by explaining what notional_usd actually buys — the exact notional is sized alongside the $100/$1k/$10k/$50k tiers, producing entry slippage, exit simulation, and max_safe_notional_usd. The buy/sell `side` parameter is never discussed in the description, leaving that one to the schema.

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-and-resource: a pre-trade GO/HOLD/BLOCK gate for a Base ERC-20 swap, enumerating the checks performed (honeypot/sellability, admin controls, Uniswap v3 liquidity vs. trade size). It is clearly not a generic token-security scan, but it never names sibling gate_swap_preview or chain_token_security, so the agent must infer which gate variant to call.

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?

"Pre-trade" implies the moment to use it, and the pricing sentence implies a paid, decision-grade call versus something thinner. But there is no explicit when-not guidance, no mention that a gate_swap_preview sibling exists, and no stated prerequisites (e.g., wallet/payment setup required before the $0.005 charge).

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, the description carries the full burden and does well: it discloses the zero-cost nature, the demo-only token scope, that results are live rather than cached, and which fields the paid tool adds plus the paid_adds block. It does not mention rate limits, freshness guarantees, or what a BLOCK verdict means operationally.

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 key differentiator (free sample, no payment) and the scope (demo tokens) are front-loaded, and each subsequent clause adds a distinct fact about the paid tier. Slightly dense with backticked field names, but nothing is redundant.

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?

No output schema exists, so the description must convey return shape, which it does by asserting the output mirrors gate_swap and naming the withheld paid fields via paid_adds. It stops short of describing the actual verdict fields, leaving the agent dependent on knowledge of the sibling tool's output.

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%, with enums and defaults already documented for side, token, and notional_usd, so baseline is 3. The description only reinforces that the token must be a demo Base token, adding no syntax, units, or interpretation beyond the schema.

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: a GO/HOLD/BLOCK pre-trade decision for a demo Base token, and explicitly distinguishes it from the sibling gate_swap by calling itself the free sample of it. An agent can tell exactly which tool to reach for without opening 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?

The free-vs-paid framing ('FREE live sample... No payment required', paid adds sizing) gives clear context for choosing this over gate_swap, and the demo-token whitelist bounds its use. It never states an explicit exclusion such as 'do not use for real position sizing', leaving that inference to the agent.

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 provided, the description carries the full burden. It discloses the $0.005 per call cost and the data fields, but does not mention rate limits, authentication requirements, or idempotency. For a read-only data tool, the transparency is moderate.

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 description is a single sentence that front-loads purpose and lists key fields efficiently. It is somewhat dense but contains no fluff. Could benefit from slight restructuring for readability, but overall concise.

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 the absence of an output schema, the description comprehensively lists all returned fields. It covers cost and ordering. However, it does not describe the JSON structure or pagination behavior, leaving some gaps for a complex tool.

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 baseline is 3. The description does not add extra meaning beyond the schema's parameter descriptions (limit and query). The ranking by volume24hr is implied default ordering, not a parameter.

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 explicitly states it provides 'Live Polymarket prediction-market data' and lists specific fields (outcomes, prices, volume, etc.), clearly differentiating from siblings like pm_markets_preview. The verb 'provides' and resource 'Polymarket prediction-market data' are specific.

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?

The description implies usage for live market data and mentions cost, but lacks explicit guidance on when to use this vs alternatives (e.g., pm_markets_preview). No when-not-to-use or prerequisite conditions are stated.

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, the description effectively communicates that this is a free, read-only preview returning a single sample. No hidden behaviors are indicated.

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 concise sentences with no waste, front-loading the key point 'FREE top-1 sample'.

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 output schema or annotations, the description adequately explains the tool's purpose and free nature. Could be slightly improved by hinting at output format.

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?

There are no parameters, so baseline is 4. The description adds context about what the tool does without needing parameter details.

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 provides a free top-1 sample of live Polymarket prediction markets ranked by volume24hr, distinct from the sibling pm_markets tool.

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?

The description mentions 'FREE' and 'no payment required,' implying it's a preview, but fails to explicitly state when to use this instead of pm_markets or other 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, the description fully discloses behavioral traits: it returns only issue count, severity breakdown, risk score, and verdict, but NOT which tools or evidence. Also mentions it's free and requires no payment, implying no destructive side effects.

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?

Four concise sentences, each adding value: purpose, return details, limitations, and usage guidance. No redundant information. Front-loaded with the core action.

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 a single parameter and no output schema, the description covers all necessary information: what the tool does, what it returns (and does not return), and when to use the paid sibling. Fully adequate for correct invocation.

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?

Only one parameter 'url' with 100% schema coverage. The description adds minimal context beyond the schema (e.g., 'free preview-scan'), but the schema itself is clear. Baseline 3 is appropriate as the parameter semantics are already well-defined.

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?

Explicitly states it's a free preview scan for tool-poisoning/prompt-injection on MCP servers. Clearly distinguishes from the paid scan_mcp_server sibling by specifying it returns only summary stats, not detailed findings.

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?

Provides explicit guidance: use this free preview first; if issues found, call paid scan_mcp_server for itemized findings and remediation. This clarifies when to use this tool vs the paid alternative.

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?

No annotations are provided, so the description carries the full burden and does it well: it explains the fetch-then-static-analyze behavior, the return shape (findings, 0-100 risk score, verdict), and the payment requirement (x402, $0.005 USDC). It omits edge cases such as unreachable targets or timeouts, so it stops short of 5.

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-loads the purpose in the first sentence, then layers analysis categories, return values, and cost. Dense and mostly waste-free, though the parenthetical OWASP codes and dual-pricing clause add some load for marginal benefit.

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 compensates by explaining the return values (findings + risk score + verdict). The single input is documented in the schema, and the payment model is disclosed, leaving nothing an agent needs to invoke 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?

Only one parameter (url) with 100% schema description coverage, so the schema already documents its meaning fully. The description adds no syntax, format, or constraint details beyond what the schema provides, warranting the baseline 3.

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 (Security-audit) and resource (target MCP server) with a scope enumeration: prompt-injection/tool-poisoning plus the five static analysis categories. An agent immediately knows this is a security-scanning tool, distinguishing it from the chain_*/crypto_*/defi_* siblings.

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?

Pricing context (x402 at $0.005/scan vs. $0.05 HTTP variant) implies a cost-based selection condition, but it never states when to choose this over the obvious sibling scan_mcp_preview or names any alternative. Usage is implied rather than prescribed.

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?

No annotations exist, so the description carries the full burden and does well: it states the return fields (will_revert, revert_reason, gas_used, asset_changes), discloses the cost ($0.005 USDC via x402), and confirms keyless/no-API-key operation. It doesn't explicitly say it sends no transaction or whether payment must be pre-approved, which keeps it short of a 5.

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 core question and dry-run mechanism, then returns, then usage. Dense and mostly waste-free, though 'Keyless ... with no API key' repeats the same point and 'Tenderly/Alchemy-class' is marketing filler.

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 4-param simulation with no output schema and no annotations, the description is nearly self-sufficient: it names the return fields, the payment model, and the pre-send use case. A small gap remains around x402 payment mechanics and whether any state is affected.

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 the baseline is 3. The description largely restates the schema (from, to, optional 0x data, value in wei) without adding format or constraint detail the schema doesn't already cover.

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?

Opens with a specific question ('Will this Base transaction revert?') and a concrete verb+resource: a prospective-tx dry-run via eth_simulateV1 on Base. It distinguishes itself from general chain tools, but never names or differentiates itself from the sibling simulate_preview, leaving ambiguity about which simulation variant to pick.

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?

Explicit context: 'Use before a swap/approve/transfer or alongside gate_swap.' The pre-send timing is clear. However, there is no exclusion guidance and no mention of when simulate_preview or chain_tx would be the better choice.

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, the description carries the burden and does disclose the key traits: no cost, no payment, and a benign 0-value call, so the agent knows this is a harmless sample rather than a real execution. It falls short of saying whether the output is canned/static data or reflects live chain state, which matters for trust.

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 front-loaded sentence leading with 'FREE sample' and the output field names, with no redundant restatement. Dense but every clause earns its place.

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 zero-param tool with no output schema, the description helpfully enumerates the return fields (will_revert/gas_used/asset_changes) and the cost model, which is largely sufficient. Only the fidelity of the sample data (static vs live) is left unstated.

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?

Zero parameters, so the baseline is 4; the schema is empty and the description correctly implies no inputs are needed. It adds the useful note that the call is a 0-value/benign invocation, clarifying why no tx payload is required.

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: a free sample dry-run of a prospective transaction that returns will_revert/gas_used/asset_changes. It is clearly a preview of the paid `simulate` sibling, though the sibling itself is never named, so the differentiation is implied rather than explicit.

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 you pay' and 'FREE sample' imply this is the zero-cost preview to call ahead of the paid path, which is useful routing signal. However, it never names `simulate` or says the preview is insufficient for a real/production decision, so the agent must infer the boundary.

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 supplied, the description carries the full burden and does so: it declares the tool is read-only, that it fetches once and 'never pays', that it is not a settlement guarantee, and that it costs $0.005 USDC per call via x402 ($0.001 direct HTTP). It also discloses side-effect-relevant behavior such as the flapping endpoint downgrading PAY to CAUTION and the absolute >=$1,000 trap tripping AVOID regardless of self-consistency.

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 lead question is well front-loaded, but the body is one very long run-on sentence chained with 'AND ... AND ... AND', making the seven distinct checks hard to parse on a first read. Dense all-caps emphasis (LIVENESS, PRICE TRAP, MATCH | OVERCHARGE | UNDERCHARGE) aids scanning somewhat but the structure is not cleanly segmented.

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, multi-check tool with no output schema and four parameters, the description covers the verdict vocabulary (PAY | CAUTION | AVOID), per-check fix hints, latency in the return, pricing of the call itself, and the read-only caveat. An agent has everything needed to decide whether to invoke it and how to interpret 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 coverage is 100%, so the baseline is 3; the description goes beyond it by explaining consequences: max produces price_trap.exceeds_caller_max, samples runs a settle-consistency/latency burst that can downgrade the verdict, and omitting advertised triggers a self-check against /.well-known/x402. It adds outcome semantics rather than just restating the parameter types.

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 and resource: a pre-payment validation of an unknown x402 URL, enumerating exactly what is checked (402 challenge/accepts[], liveness, price trap, prompt injection, OFAC/scam screening, advertised-vs-live price). The 'pre-payment' framing cleanly separates it from the sibling x402_receipt_verify, which is post-payment, without needing to name it.

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?

The opening question 'Should an agent pay this x402 endpoint?' plus 'pre-payment check of an UNKNOWN x402 URL' establishes the use case, and it tells the caller when to supply max, advertised, and samples. It stops short of explicit when-not-to-use guidance or naming alternatives such as x402_receipt_verify for already-paid receipts.

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?

No annotations are supplied, so the description carries the full load, and it does disclose key traits: read-only ground truth, live Base-mainnet RPC read, a $0.005 USDC x402 charge per call, and the explicit limit that it confirms settlement 'not off-chain resource delivery'. However, it omits latency, rate limits, caching, and what happens when the live 402 fetch fails (the UNVERIFIED path is named but not explained). Solid but not exhaustive for an unannotated paid tool.

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-loads the agent's actual question ('Did my x402 payment actually settle?') then gives mechanism, inputs, return values, and cost in a logical order, with zero filler sentences. It is dense and slightly overpacked into one paragraph, but every clause carries information an agent needs.

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 and no annotations, the description compensates by enumerating all seven verdict values, describing the return payload (matched transfer plus all USDC transfers in the tx), and stating the pricing model. That is enough for an agent to call it and interpret the result without opening anything else.

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 100%, so the 3 baseline applies, but the description adds real meaning beyond the schema: it explains that url resolves payTo/amount from the resource's live 402 while payto/expect 'bind it directly' without fetching, clarifying the mode switch between the two paths. It also names expect's unit ('USDC dollars (e.g. 0.004)') consistently with the settlement amount being reconciled.

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?

Opening question plus a specific verb+resource ('reads the tx receipt from Base mainnet, decodes its USDC Transfer events, reconciles against payTo + amount') tells the agent exactly what it does. It explicitly positions itself against the sibling x402_preflight ('the other half... which checks BEFORE paying'), so no schema-opening is needed to choose between 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?

States the trigger clearly ('POST-payment'), the required inputs ('bring your Base settlement tx hash + the resource URL you paid'), and the alternative with its condition ('x402_preflight... checks BEFORE paying'). It also names a cheaper direct HTTP route, giving an explicit opt-out path.

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, the description carries the burden and does well: it discloses cost (free), auth (keyless), read semantics (dual-RPC receipt read + USDC Transfer decoding), and the full set of outcome states. It does not mention rate limits or failure modes when RPCs disagree, 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?

Two sentences, front-loaded with the cost/auth/network qualifier before the mechanics and the sibling routing. Dense but zero waste, and the enumerated status list is compact rather than prose-expanded.

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 compensates by enumerating the six possible return states, which is exactly what an agent needs to branch on. It is thin on what accompanies a status (decoded transfer amount, recipient mismatch detail) and on the binding rules when payto does not match.

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 100%, so all three parameters are already documented, including expect's USDC unit. The description restates the same facts ('pass a tx hash plus payto (and optionally expect, in USDC)') without adding format, validation, or edge-case meaning. 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 and resource ('x402 settlement check on Base') plus the exact inputs and the network. It explicitly distinguishes itself from the paid sibling x402_receipt_verify, so an agent can route without opening 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?

Makes the selection condition clear: this tool binds to a payTo you already hold, while resolving payTo from a live 402 url requires the paid x402_receipt_verify. It also flags the free/keyless nature, which is a strong selection signal. No explicit 'do not use when' statement beyond the sibling routing.

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?

No annotations exist, so the description carries the full burden, and it discloses several non-obvious traits: a per-call price ($0.005 USDC via x402 on MCP tools/call, $0.01 direct HTTP), the signals the verdict is derived from (APY 1d/7d/30d, stability forecast, il7d, sigma, outlier flag, TVL), and the Base-chain constraint on the token parameter. It does not cover failure behavior for invalid poolIds, latency, or caching.

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?

Purpose and output shape are front-loaded, and the long middle sentence is a compact enumeration of inputs rather than filler. The pricing and routing note is useful but slightly crowded into the same block; a small tightening would make it a 5.

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 and no annotations, the description responsibly covers the return contract (verdict enum, risk score range, field-cited reasons) and the cost model. Remaining gaps are edge-case handling and routing to the preview variant, which keep it below a 5 for a paid, non-read-only-flagged tool.

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 already 100%, so the baseline is 3, but the description adds real meaning: 'pool' must be the 'pool' field from defi_yields (a concrete provenance hint), and 'token' is an optional 0x address on Base that only adds a honeypot-check pointer rather than changing the verdict. That clarifies the effect of each parameter beyond the schema's own text.

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 and resource ('per-pool DeFi yield-entry go/no-go') and defines the exact output artifact: a SUSTAINABLE | DECAYING | OUTLIER | AVOID verdict plus a 0-100 risk score. It explicitly contrasts with the sibling defi_yields, which supplies the raw pool data this tool consumes, so an agent can pick between them without opening 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?

Gives a clear sequencing rule: 'The should-I-enter-THIS-pool call after defi_yields,' which tells the agent when to invoke it and what must precede it. It also notes the direct HTTP route as an alternative transport. It stops short of mentioning the yield_entry_verdict_preview sibling or stating when not to use the tool (e.g. non-Base tokens, missing poolId).

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, the description carries the full burden and does disclose real behavior: the target pool is fixed (current top-TVL), the call is free, and the payload is a packaged verdict plus risk score. It stops short of saying whether the data is live or illustrative, or noting rate limits/repeat-call behavior, which matters for an agent deciding how much to trust the sample.

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 'FREE sample', then scope, then return shape — good ordering in three short sentences. Minor waste: 'FREE' and 'No payment required' say the same thing twice.

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?

No output schema exists, so the description must describe the return value, and it does name the verdict enum (SUSTAINABLE/DECAYING/OUTLIER/AVOID) and the accompanying risk score. Combined with the zero-parameter schema, that is nearly everything needed to call it correctly; only the data's freshness/provenance is left ambiguous.

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?

Zero parameters, so the baseline is 4. The description earns it by explaining why the schema is empty — the pool is always the current top-TVL pool — which prevents an agent from hunting for a pool-address parameter that does not exist.

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 (sample yield-entry verdict) and narrows the scope to 'the current top-TVL pool', which is exactly the kind of detail an agent needs. The 'preview'/'before you pay' framing implicitly separates it from the sibling yield_entry_verdict, though it never names that sibling.

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?

The phrase 'before you pay' implies when to reach for it (inspecting output shape prior to a paid call), but there is no explicit 'use yield_entry_verdict when you need a real verdict for a specific pool' routing statement. Usage is inferable rather than stated.

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