counterparty-intelligence

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

Annotations already mark the tool as read-only, idempotent, and non-destructive. The description adds valuable context: it is free (with a cost noted for a more detailed call), it is 'read-only, not financial advice,' and it returns specific fields (economic_class, balance, verdict). This goes beyond the annotations to inform the agent about side effects and limitations.

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, well-structured paragraph that efficiently conveys purpose, output, cost, and disclaimers. It avoids unnecessary words and is front-loaded with the main action. Minor improvement could be separating the cost note for clarity, but it remains concise and informative.

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 a good annotation set, high schema coverage, and an output schema present, the description is nearly complete. It explains the return fields, use case, and cost implications. The only minor gap is not explicitly stating that the output schema provides detailed field types, but that is covered by the output schema itself.

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 description for 'address' is present (coverage 100%), stating the format 'x402 agent wallet to credit-check (0x + 40 hex)'. The main description does not add further parameter semantics, but the high schema coverage means the burden on the description is low. The description provides no additional usage context for the parameter beyond what the schema offers.

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's purpose: 'Credit-check any x402 agent wallet before you rely on it or extend it service.' It specifies the resource (agent wallet) and the action (credit check). The sibling tools (e.g., check_counterparty, crest_score) suggest related functionality, but the description uniquely positions this as a credit check focused on economic class and creditworthiness, making it 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 provides clear when-to-use guidance: 'before you rely on it or extend it service.' It also mentions the tool is free and hints at cost for deeper reads, which helps in decision-making. However, it does not explicitly contrast with siblings or state when not to use it, missing some differentiation opportunities.

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?

Annotations already declare readOnlyHint=true, destructiveHint=false. Description reinforces read-only nature and adds valuable context: free call, pricing for full gate, returns risk_level and reason codes. No contradiction.

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?

Three sentences with clear imperative, result description, and extra context. No wasted words, front-loaded with key 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?

With one parameter and an output schema, the description explains purpose, usage guidance, returns, and pricing. Fully adequate for agent selection and 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?

Schema has 100% coverage with adequate description of 'address' parameter. Description does not add meaning beyond the schema, 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?

Description clearly states it returns risk_level and reason codes for a wallet before transfers/trades/settles, using Crest counterparty intelligence. Distinguishes from sibling tools like check_counterparty and token_risk by positioning as a pre-action risk gate that helps skip bad addresses.

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 says 'Call BEFORE your agent transfers, trades, or settles to a wallet.' Provides context on pricing and suggests it's a lightweight check, but does not explicitly state when not to use or compare to 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?

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false, so the safety profile is clear. The description adds context about cost (free vs. paid) and the result format (plain verdict), which is useful but not critical beyond 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?

The description is highly concise, consisting of two informative sentences and a tagline. It is front-loaded with the core purpose and delivers maximum information in minimal space.

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 that an output schema exists (not shown but indicated), the description adequately covers return values by naming verdict types and safety flag. Sibling tools are distinct enough to avoid confusion. Slightly missing explicit mention of the full output schema but is sufficient.

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 schema already describes the parameter fully ('the Base/EVM address your agent is about to pay (0x + 40 hex)'). The description does not add additional semantics about the parameter beyond what is in the schema, so 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?

The description clearly states the tool's purpose: to check the counterparty before paying over x402. It lists specific verdicts (real service, buyer, relayer, treasury) and notes whether it's safe to pay, distinguishing it from siblings like onchain_profile or pm_counterparty.

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 provides usage context ('Before your agent pays an address over x402') and an alternative paid option. Could be improved by explicitly stating when not to use it, but the guidance is clear.

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?

The description discloses important behavioral traits: creation vs. read-only modes, one-time display of passport_key, optional wallet binding, and that it's free. Annotations already indicate non-read-only and non-destructive, but the description adds valuable context beyond 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?

The description is relatively short (4 sentences) and well-structured: opening metaphor, then clear mapping of parameters to actions. It avoids unnecessary detail, though the first sentence is slightly fluffy.

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 multi-mode nature and presence of an output schema, the description covers all modes, return values, and the one-time key note. It lacks details on parameter interaction errors or permissions, but not critical for decision-making.

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 is 3. The description adds meaningful context: explains that no args triggers creation, passport_key loads with key shown once, agent_id views public info, and wallet binds for reputation. This goes beyond schema descriptions.

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's purpose: managing a persistent agent passport. It distinguishes three modes based on parameters (no args=create, passport_key=load own, agent_id=view public). While not explicitly differentiating from sibling tools, the verbs and resource focus make the purpose clear.

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 usage context for each parameter but does not explicitly say when to use this tool over alternatives. It implies usage based on whether you want to create, load, or view passports, but lacks direct guidance on exclusions or comparisons to sibling 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?

Annotations already provide readOnlyHint, openWorldHint, idempotentHint, destructiveHint=false. Description adds behavioral details: matches content and tags, two modes of operation (keyword or recent). No contradiction.

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 purpose, no redundant information. Every sentence 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?

Covers the two main use cases and passport_key requirement. Output schema exists for return values. No discussion of errors or limits, but overall sufficient for a simple retrieval 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?

Input schema has 100% coverage with clear descriptions. Tool description reinforces parameter purpose (keyword match for 'query', max results for 'k'), but adds minimal new value beyond 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?

Clearly states the tool searches memories by keyword or retrieves recent entries. The verb 'search/get' and resource 'your own memory' are specific. Distinguishes from sibling 'crest_remember' which likely writes memories.

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?

Specifies requirement for passport_key but does not explicitly state when to use vs alternatives like crest_passport or crest_score. Usage context is implied but no exclusion criteria.

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?

Annotations indicate non-readOnly, non-idempotent, non-destructive. The description adds value by explaining the hash-chaining (tamper-evident) and specifying return values (entry hash, memory_root) and the PII prohibition. Extra context beyond annotations, no contradictions.

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?

Three sentences, front-loaded with purpose, followed by technical detail and requirements. No wasted words; every sentence 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?

The description covers purpose, output, and a key constraint. An output schema exists, so return values don't need elaboration. It could mention prerequisites (e.g., passport must exist) or error conditions, but given tool complexity, it is sufficiently 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?

Schema description coverage is 100%, so baseline is 3. The description adds meaningful guidance with the PII warning for the content parameter, which is critical for compliance. It does not add syntax details beyond the schema, but this extra context raises the score.

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 verb 'Append' and the resource 'Crest memory', specifying the types of data (fact, decision, outcome, note). It distinguishes from siblings like crest_recall (read) and crest_verify (verify) by describing the hash-chain mechanism that makes memory provable and tamper-evident.

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 by requiring 'passport_key' and warning against storing human personal data. However, it does not explicitly state when to use this tool versus alternatives like crest_recall or crest_passport, though the purpose is clear enough for inference.

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?

Annotations already indicate read-only, idempotent, non-destructive. Description adds that it's free, not financial advice, and built on specific data sources. Provides example output and notes a paid detailed version, going beyond annotation basics.

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?

Description is moderately lengthy but well-structured, starting with purpose. Example and additional details are valuable. Minor redundancy (e.g., 'two axes' restated) but overall efficient.

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 output schema exists (not shown) and description already summarizes output fields (crest_score, band, decision), the description fully covers purpose, parameter, usage context, and return structure. No gaps for a read-only 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 covers the single parameter with a description; description reinforces with an example and context about x402 wallet scoring. No additional constraints needed beyond what's provided.

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 the tool assesses creditworthiness of x402 wallets with two axes (solvency, liveness) and outputs a band and decision. Distinguishes from siblings like 'agent_credit' and 'check_counterparty' by specifying the specific scoring mechanism and output format.

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 recommends calling before paying or extending service. Mentions a paid full report as an alternative for more detail. Lacks explicit 'when not to use' but provides sufficient context for appropriate invocation.

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?

Annotations already declare readOnlyHint true, idempotentHint true, destructiveHint false. Description adds context: 'Read-only, not financial advice' and explains the on-chain resolution process. No contradictions.

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?

Three sentences, efficient and front-loaded with purpose. Could be slightly tighter by omitting some redundancy, but overall well-structured.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given output schema exists, description covers input variations and expected output fields. Adequately complete for a verification tool with 3 optional parameters.

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%, but description adds meaning beyond schema: explains that erc8004_id resolves on-chain identity and overlays behavioral read. Provides usage context for each identifier type.

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 uses a specific verb ('look up') and resource ('Crest passport'), and includes key fields (standing, days active, memory depth, on-chain role). It clearly distinguishes from sibling tools like 'crest_passport' or 'crest_score' by focusing on verification before trust/pay.

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 states when to use: 'Before you trust or pay another agent'. Lists accepted identifiers (agent_id, wallet, erc8004_id). Does not explicitly state when not to use, but sibling list provides implied 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?

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, so the safety profile is clear. The description adds context about what data is returned (account type, balance, tx count) and the 'free coverage check' aspect, but does not disclose potential rate limits or authentication requirements.

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, front-loading the key actions and outputs. Every word is essential and there is 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 of the tool (one parameter, no nested objects) and the presence of an output schema, the description sufficiently covers the main data points (account type, balance, tx count) without needing to detail return values. It is complete for its purpose.

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 100% coverage for the single parameter 'address', with a clear description already present. The tool description does not add new semantics beyond what the schema provides, so it meets the baseline.

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 'quick public snapshot' of a Base/EVM address, listing specific data (account type, balance, tx count). The verb 'snapshot' and resource 'Base/EVM address' make the purpose distinct, though it does not explicitly differentiate from sibling tools like agent_credit or check_counterparty.

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 coverage check' but provides no explicit guidance on when to use this tool versus alternatives. It implies use for quick lookups, but does not specify exclusions or contrast with sibling 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?

Annotations already indicate read-only, idempotent, open-world, and non-destructive behavior. The description adds that it is 'not betting advice' and that it works on resolved markets, implying historical rather than real-time data. No contradiction with annotations; cost note for deeper read is additional 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?

The description is three sentences with the primary action front-loaded. It includes a tagline and cost note, which are valuable but slightly extend the length. Overall, it is efficient and avoids 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?

Given the low parameter count and the presence of an output schema, the description adequately explains what the tool does and how it works (by realized edge, with confidence). It could be more explicit about the output structure, but the mention of confidence and the existence of an output schema compensate.

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 the single parameter 'address' with a clear description of format. Since schema coverage is 100%, the description adds no further parameter-level detail beyond what the schema provides, which is acceptable but not enhanced.

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 classifies a Polymarket trader wallet into three categories (sharp money, dumb money, neutral) using realized edge and provides confidence. The verb 'classify' and resource 'Polymarket trader wallet' are specific, and the mention of 'know who is on the other side' distinguishes it from siblings like onchain_profile.

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 advises using the tool 'before your agent acts,' giving clear context for when to invoke. It also notes that a deeper read requires a $0.02 x402 HTTP call, implying this tool is a free initial assessment. However, it does not explicitly list alternatives or when not to use it.

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?

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint. The description adds significant behavioral details: it scans for dangerous powers (mint, blacklist, pause, upgrade) and checks who controls them, how control is scored on the Crest settlement graph, and that the same powers can be safe or risky depending on the controller. It also notes the tool is free but a full report costs $0.05, and states it is read-only and not financial advice. All information is consistent with 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?

The description is sufficiently concise and front-loaded, starting with the primary use case. It packs useful details (scanned powers, controller assessment, example, pricing, read-only note) without unnecessary fluff. Minor non-essential detail: 'By Crest Deployment Systems' could be omitted, but overall it is well-structured.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool has an output schema and is a single-parameter read-only check with comprehensive annotations, the description is complete. It covers the domain (Base tokens), the risk factors scanned, how trust is evaluated, and even provides an example output. No essential context is 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 has 100% coverage with a clear description for the single parameter 'address'. The description reinforces that the address must be a Base ERC-20 token contract address (0x + 40 hex) and provides a concrete example call, adding substantial semantic value 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 the tool's purpose: 'Call this before your agent buys, swaps, or LPs into a Base token, to check if it is a rug, honeypot, or scam.' It specifies the action (scan) and resource (token risk), fully distinguishing it from siblings like 'crest_score' or 'check_counterparty'.

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 states when to use: 'before your agent buys, swaps, or LPs into a Base token.' While it does not explicitly mention when not to use or list alternatives, the context is clear and the usage scenario is well-defined.

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