NullClear Arbiter

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

Annotations already declare readOnly/idempotent/non-destructive/openWorld, so the safety profile is covered. The description adds substantive behavior beyond them: the score is a 0-100 scale, the inspection surfaces clearing reliability and Sybil wash-trade penalty flags, and the data lives on Base. It omits rate limits, auth requirements, and failure behavior for unknown agent IDs.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single dense sentence with no filler, and the core resource (trust score) is front-loaded before the secondary facets. Slightly cramped as an enumeration crammed into one clause, but nothing is wasted.

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

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

With no output schema, the description carries the return-value burden and does so reasonably by naming the score range and the four data facets an agent will receive. Read-only annotations cover the safety side. Minor gap: it doesn't indicate what happens when an agent is unregistered or how the flags are presented.

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% — agentId (ERC-8004 token ID with an example) and chainId (Base mainnet/Sepolia) are fully documented in the schema. The description's only contribution is the phrase 'on Base', which loosely aligns with the chainId default but adds no new syntax or constraint.

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 ('Inspect') and resource (an AI agent's trust/reputation profile) and enumerates the facets returned: trust score, clearing reliability, Sybil flags, KYA backing. However, it never distinguishes itself from the sibling nullclear_verify_kya_mandate, whose domain ('corporate KYA backing') it explicitly overlaps.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is only implied — an agent can infer this is the read-only lookup to run before trusting or transacting with an agent, but the description gives no when-to-use trigger, no prerequisites, and no routing versus verify_kya_mandate or escrow_x402_call.

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, openWorldHint and destructiveHint=false, so the safety profile is covered. The description adds genuinely useful context beyond them: it is spread-verified across multiple exchanges, emits cryptographic invariant receipts, needs no configuration, and is capped at 10 free daily calls.

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 core action and resource. The pricing/configuration note in the second sentence is relevant and compact; nothing is wasted.

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

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

With no output schema, the description does enough by noting the return includes spread-verified prices and cryptographic receipts, and it flags the free-call limit. It is slightly thin on the exact receipt format, but for a low-complexity read tool with full annotations this is close to 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% for the single 'pair' parameter, so the baseline is 3. The description does add one supported value not present in the schema examples (BASE/USDC), but otherwise does not expand on parameter semantics.

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 gives a specific verb ('Fetch') and resource ('multi-exchange spread-verified crypto spot prices') and enumerates the supported pairs, making the tool's function immediately legible. It does not explicitly contrast itself with the sibling tools (reputation, escrow, token audit, etc.), but the resource is distinct enough that confusion is unlikely.

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 guidance on when to use this over the sibling NullClear tools, nor any stated conditions or prerequisites beyond 'zero configuration'. The mention of '10 free daily calls' hints at a rate limit but does not tell the agent when this tool is the right 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?

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so the safety profile is covered. The description adds genuinely new behavioral context by stating that a NullClear-protected Zero-Loss Proxy URL is returned for each endpoint, which matters given there is no output schema. It still omits pagination/result-count 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, no filler, with the core purpose front-loaded and the return-value detail in the second sentence. 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?

With no output schema, the description usefully explains what comes back (per-endpoint Zero-Loss Proxy URLs), and all five parameters are documented in the schema. It stops short of covering result ordering, pagination, or empty-result behavior, but nothing critical to a correct call 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?

Schema description coverage is 100% at five parameters, so the schema fully documents query, category, minUptime, maxLatencyMs and verifiedOnly. The description maps loosely onto the first four but adds no syntax, ranking or range detail beyond the schema, making the baseline 3 correct.

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 gives a specific verb+resource: search the live NullClear Ecosystem Directory for audited x402/ERC-8004 APIs, with the filter dimensions named. It is clearly a discovery/listing tool distinct from operation tools like nullclear_escrow_x402_call, though it never names a sibling to sharpen that distinction.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied: an agent should reach for this to find endpoints before invoking them. However, there is no explicit when-to-use statement, no when-not, and no pointer to the sibling that actually performs the x402 call, leaving the routing to 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 declare readOnly=false, idempotent=false, and openWorld=true, but the description adds genuinely new context: payment settles only if the upstream response satisfies the schema contract, and no wallet setup is needed for trial calls. It stops short of explaining refund/escrow-release behavior on failure or latency of settlement.

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 tight sentences with the core value proposition (conditional settlement) front-loaded, followed by the trial-call incentive. No filler, though the trial-call sentence is more marketing than operational guidance.

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 10-parameter tool with deeply nested objects and no output schema, the description covers the escrow guarantee but says nothing about the return payload, failure modes, or how fallbacks/invariants/spendPolicy interact with settlement. It is adequate because the schema is richly documented, but not 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 90%, so the schema itself documents targetUrl, invariants, fallbacks, spendPolicy, and the rest. The description only gestures at jsonSchema ('your schema contract') and does not clarify invariants, spend firewall limits, or fallback routing semantics, so it adds little beyond structured data.

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 verb (Execute) and resource (x402-gated HTTP API call) plus the mechanism (NullClear deferred schema escrow), which is distinctive enough to separate it from generic fetch siblings. It never explicitly contrasts itself with nullclear_safe_fetch, so sibling differentiation is implied 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?

There is no guidance on when to choose this over nullclear_safe_fetch or when not to use it, despite the sibling list containing an obvious alternative fetch tool. The '10 free daily trial calls' line hints at onboarding but is not usage guidance for selection.

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 establish the safety profile (readOnly, non-destructive, idempotent, open-world). The description does add real behavioral context beyond them: guards for LLM refusals, 5xx crashes, and empty JSON, plus a 'cryptographic execution receipt'. But it never says what a guard trip actually produces (error vs. transformed payload) or how the receipt is surfaced, so the added context is suggestive rather than actionable.

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 core function and followed by the protective behavior. Every clause is doing some work, though the coined guard names are longer than they need to be for the information conveyed.

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

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

There is no output schema, so the description carries the full burden of explaining what comes back — yet it only alludes to a 'cryptographic execution receipt' without saying how or where it is returned. Failure semantics for the three named guards are also unspecified, which is a meaningful gap for a tool whose entire value proposition is guarding responses.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 67%: url and body are documented in-schema, and method is self-documenting via enum+default. The description adds nothing about parameters, and its 'drop-in URL fetcher' framing arguably undersells the POST-with-body capability. With the schema carrying most of the burden, 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 states a concrete verb+resource: it fetches a URL and verifies the response through guards. It is clearly distinguishable from all siblings (reputation, oracle, escrow, audit, KYA, wallet risk), none of which fetch URLs. However, the purpose is wrapped in proprietary jargon ('Canonical LLM Refusal Guard') that obscures rather than sharpens what it actually does.

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 guidance on when to choose this over a plain HTTP fetch or over any sibling tool, and no stated preconditions or exclusions. 'Zero-config drop-in' implies a replacement for a bare fetcher, but the agent must infer that on its own.

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 readOnly, idempotent, non-destructive, open-world behavior, so the safety bar is covered. The description adds genuinely useful operational context beyond the annotations: it runs against a third-party service (NullClear Bazaar), needs zero configuration, and is rate-limited to 10 free daily calls.

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 audit action and its check list before the quota detail. The 'Works out-of-the-box with zero configuration' phrasing is mildly promotional but the quota number that follows is actionable, so waste is minimal.

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 read-only audit tool with no output schema, the description covers what is checked and the calling constraints, which is sufficient to call it correctly. It stops short of describing the returned report's shape (scores vs. booleans), a small residual gap given no output schema exists.

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 is a single parameter with 100% schema description coverage, including a default and a USDC example, so the schema does the heavy lifting. The description's 'any Base ERC-20 token address' adds only a mild scoping constraint (Base chain, ERC-20 contract, not a wallet) that is already largely present in the schema 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 (Audit) and resource (Base ERC-20 token address) plus the exact checks performed: honeypot risk, buy/sell taxes, verified bytecode, x402 compatibility. That is enough to distinguish it from wallet-oriented siblings like nullclear_wallet_risk_score, though no sibling is named explicitly.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies the triggering condition (you have a Base ERC-20 token address and want a security read), and the 'zero configuration / 10 free daily calls' note tells the agent it can be called immediately. It never states when NOT to use it or names an alternative tool for related questions (e.g. wallet risk), so guidance stays implicit.

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, destructiveHint=false and openWorldHint, so the safety profile is covered. The description adds the useful scope of what is verified, but says nothing about what a failed/expired mandate does or what the caller receives, leaving behavioral disclosure thin beyond the 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?

A single sentence with no filler, and the core purpose is front-loaded before the enumerated checks. The comma-chained triple check is dense but each clause carries information, so size is appropriate for the tool's complexity.

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 ideally hint at the return (pass/fail, expiry, limit breach reason) so an agent knows how to consume the result; instead it only describes what is inspected. It is adequate but leaves a real gap for a verification tool whose value is in its verdict.

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 agentId, chainId (default 8453) and transactionAmountUsd are already documented in the schema. The description only loosely echoes transactionAmountUsd via 'within corporate limits' and adds no format, unit, or chain-selection nuance beyond what the schema provides; 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 (Verify) and a precisely named resource (agent's Know Your Agent corporate liability mandate), then enumerates the three things checked: mandate existence, active validity, and transaction-amount limits. It is clearly distinguishable from check_reputation and escrow_x402_call by resource, though it never names those siblings explicitly.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is only implied: the phrase 'proposed transaction amount' suggests this is a pre-transaction gate, but the description never states when to call it versus the reputation or escrow siblings, nor any prerequisite (e.g., must the agent ID be registered first). No exclusions or alternatives are given.

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, destructiveHint=false and openWorldHint, so the safety profile is covered. The description adds genuinely new behavioral detail not present in structured fields: zero-configuration operation and a concrete rate limit of 10 free daily calls. It stops short of describing return shape or data-freshness 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 front-loaded sentences: the capability and the covered risk categories come first, the operational caveat second. No filler, though the parenthetical pricing note is slightly promotional rather than functional.

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 two-parameter, read-only screening tool with no output schema, the description is largely sufficient: it names the data sources checked and the operational constraints. The remaining gap is routing between this and the sibling reputation/KYA tools, which the description does not resolve.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so both parameters are already documented, and the description's phrase 'any wallet or agent address on Base' merely echoes the walletAddress/chainId semantics without adding format or edge-case detail. Baseline 3 is appropriate when the schema carries the parameter burden.

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 (Check) applied to a clear resource (wallet or agent address on Base) and enumerates the three risk categories it inspects (OFAC sanctions, Sybil wash-trading concentration, ERC-8004 counterparty reputation). That is well beyond a tautology, though it does not explicitly distinguish itself from the overlapping nullclear_check_reputation or nullclear_verify_kya_mandate 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?

The description implies the use case (pre-transaction risk screening of a counterparty) and notes zero-config setup, but offers no explicit when-to-use/when-not guidance and never names an alternative among its many risk-oriented siblings. Usage must be inferred rather than read.

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