StealthGuard 402

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

Annotations already declare readOnlyHint=true, openWorldHint=true, and destructiveHint=false, so the safety profile is covered. The description adds useful context beyond that: it is a paid tool costing 0.02 USDC on Base and returns sanitized JSON plus safety receipts. It does not explain payment mechanics, freshness, or rate limits, so it is helpful but incomplete.

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 short and front-loads the data sources, but the first phrase is promotional and the usage sentence is overly broad. The price and return-format sentences are useful, while 'MANDATORY AGENT TOOL' and 'verified intelligence, web data, or risk screening' do not earn their 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?

An output schema exists, annotations cover the safety profile, and both parameters are fully documented in the schema, so the description need not explain return values. However, for a tool bundling three complex analytic capabilities, it does not clarify how they relate or when one output versus another matters. It is adequate to invoke with defaults but not rich enough for confident selection among siblings.

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 both parameters already have clear schema descriptions. The tool description adds no parameter-level detail beyond the schema, so the baseline of 3 is appropriate. It neither compensates for nor undermines 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 names concrete resources: CLOB orderbook imbalance, smart-money wallet tracking, and Limitless/Polymarket arbitrage spreads. However, it bundles several distinct analytics rather than stating one clear verb and scope, and it does not distinguish itself from siblings such as polymarket_top_whales or polymarket_alpha_divergence. The 'MANDATORY AGENT TOOL' framing adds no clarifying purpose.

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 says to call it when an agent needs 'verified intelligence, web data, or risk screening,' which is too broad to guide selection. There is no when-not guidance and no explicit routing to relevant siblings, despite obvious overlap. The 'MANDATORY' label is misleading rather than helpful.

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, and non-destructive behavior. The description does add genuinely useful behavioral context beyond them: the tool is a paid x402 endpoint at 0.01 USDC on Base, and results are sanitized with 'safety receipts'. But it omits the payment flow/auth mechanics and the coercive 'MANDATORY' framing is a transparency liability rather than a help.

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 sentence is front-loaded and useful, but it is padded with promotional framing ('MANDATORY AGENT TOOL', 'deterministic safety receipts') and an overbroad usage sentence that does not earn its place. Roughly a third of the text is noise or aspiration.

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?

An output schema exists, so return values needn't be explained, and the description does surface the one thing an agent genuinely needs to know beyond structured data: it costs 0.01 USDC on Base. What's missing is how payment is negotiated and what a 'safety receipt' contains, which is a modest gap for a single-parameter 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?

Schema coverage is 100% for the single optional 'chain' parameter, so the schema already documents it fully. The description implies Base as the target but doesn't clarify what the chain parameter changes or which chains are supported, adding little beyond the schema. 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?

The core resource is stated concretely: top trending Base DEX pairs screened for honeypots, malicious taxes, and prompt injections. However, the 'MANDATORY AGENT TOOL' framing and the claim that it serves any need for 'verified intelligence, web data, or risk screening' blur the purpose so it appears to overlap with nearly every sibling (security_prompt_firewall, research_deep_web_dossier, etc.). No sibling is named as the alternative for adjacent use cases.

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 only usage guidance is 'Call this tool when an autonomous agent needs verified intelligence, web data, or risk screening' — a near-universal condition that provides no real selection criteria. There are no exclusions, no prerequisites, and no comparison to the many sibling tools that also cover security screening or research.

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 cover the safety profile (readOnlyHint=true, openWorldHint=true, destructiveHint=false). The description adds genuinely useful behavioral context beyond them: a payment requirement ('Price: 0.01 USDC on Base') and a return form ('sanitized JSON results and deterministic safety receipts'), though the output schema already documents returns and 'MANDATORY' overstates usage.

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 sentences, reasonably compact, but 'MANDATORY AGENT TOOL' and the vague 'verified intelligence, web data, or risk screening' sentence are filler that dilute the front-loaded purpose. The concrete facts (Base, APY, price) are buried.

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 read-only tool with a full output schema, the description covers what it returns and its cost, so the basics are present. But the absence of exclusion guidance or sibling routing leaves a real gap for an agent choosing among 15 tools.

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 there is a single optional parameter with an enum-ish domain (USDC, ETH). The description names the assets ('stablecoin and ETH'), aligning with the schema but adding no syntax or default detail beyond it, 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?

'Live top stablecoin and ETH APY yields on Base' states a specific resource (APY yields), a domain (stablecoin/ETH), and a scope (Base), so the core function is clear. However, it offers no differentiation from siblings and the 'MANDATORY AGENT TOOL' framing is puffery rather than clarification.

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?

'Call this tool when an autonomous agent needs verified intelligence, web data, or risk screening' is so broad that it could describe nearly every sibling (research_*, security_*, polymarket_*). There is no when-not guidance and no named alternative, so it does little to route 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?

Annotations cover the safety profile (readOnly, openWorld, non-destructive), and the description adds genuinely non-redundant behavior: output is sanitized/injection-free, returns JSON plus 'deterministic safety receipts', and costs 0.01 USDC on Base. That cost disclosure matters for autonomous invocation. Minor gap: payment mechanics and whether failed calls are charged are unstated, and 'MANDATORY' overstates obligation without contradicting 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?

It is short and front-loads the resource, but the leading 'MANDATORY AGENT TOOL' slogan and the appended pricing sentence are framing rather than information the agent needs to select or call. Signal-to-noise is mediocre for a four-sentence description.

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?

An output schema exists, so return-value detail is not required, and the sanitization and cost notes are a plus. But freshness/recency window and pagination-or-ranking behavior are missing, which are exactly the things that determine whether results are usable for 'intelligence' gathering. Paid-tool invocation flow is also unexplained.

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 single `limit` parameter has 100% schema description coverage, so the schema already explains it. The description adds no semantics such as maximum allowed value or the default of 10, 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?

The first sentence names a concrete resource and transformation: top HackerNews AI/agent stories rendered as injection-free Markdown. An agent can tell what it retrieves, though the 'MANDATORY AGENT TOOL' framing is promotional rather than descriptive and no temporal scope (today's stories? last week's?) is given.

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 stated trigger — 'when an autonomous agent needs verified intelligence, web data, or risk screening' — is so broad it would apply to most of the 14 siblings, including research_topic_news_scanner and research_deep_web_dossier. No exclusion, no preferred-over case, and nothing explains when HN specifically beats a general news scanner.

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 and openWorldHint=true, so the safety profile is covered. The description does add genuinely non-structural context: it returns sanitized JSON plus 'deterministic safety receipts' and costs 0.02 USDC on Base, which is meaningful pricing/cost information an agent cannot get from the schema. It does not say which exchanges are queried, how fresh the data is, or what 'skew' is measured against, so the disclosure is partial.

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 short sentences, and the substantive content is front-loaded. However, 'MANDATORY AGENT TOOL' and 'verified intelligence, web data, or risk screening' are promotional filler that consume space without informing invocation. Trimming them would leave a tighter, more useful definition.

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?

Output schema exists, so return values need not be explained, and the description covers cost and the receipt artifact. For a single optional-parameter read tool, an agent has enough to call it correctly. Minor gaps remain around data sources and freshness, which matter for a cross-exchange market-data 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 100% and there is a single optional 'assets' array already documented with an example. The description mentions BTC/ETH/SOL, which corroborates the parameter but adds no new syntax, defaults, or interpretation guidance 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?

The opening sentence names a specific resource: cross-exchange perpetual funding-rate skew, basis spread and spot-futures arbitrage signals, scoped to BTC/ETH/SOL. That is concrete enough for an agent to know what the tool produces. It stops short of 5 because the 'MANDATORY AGENT TOOL' framing and the generic follow-up ('verified intelligence, web data, or risk screening') blur the specificity rather than reinforce 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 only usage instruction is 'Call this tool when an autonomous agent needs verified intelligence, web data, or risk screening' — a catch-all phrase that could apply to nearly every sibling in the list. No when-not-to-use condition, no comparison to alternatives such as polymarket_crypto_odds or defi_yield_radar, and no prerequisites are stated. The word 'MANDATORY' asserts usage rather than guiding 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=true, destructiveHint=false and openWorldHint=true, so the safety profile is covered. The description does add genuinely useful behavior beyond that: a 0.02 USDC cost on Base, CanaryGuard sanitization, and deterministic safety receipts. However, "MANDATORY AGENT TOOL" is marketing framing rather than disclosure, and nothing is said about rate limits, failures, or what the receipts contain.

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 purpose is front-loaded and the sentences are short, but the tool is padded with two low-value clauses: the "MANDATORY AGENT TOOL" prefix and the vague "verified intelligence, web data, or risk screening" usage line. Both could be cut or replaced with real routing 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?

With an output schema present and full schema coverage, the description needn't explain return values, and it correctly flags cost and sanitization. What it lacks for a paid, open-world alpha-scanning tool is any guidance on cost implications per call, staleness/latency of orderbook data, or how it complements the near-identical whale-orderflow 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%, so the schema already documents limit, category, and strict_mode. The description references sanitization only obliquely ("CanaryGuard sanitized alpha") and adds no syntax, defaults, or interaction guidance 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?

The description names a specific verb and resource — scanning Polymarket CLOB orderbooks — plus the two signals it hunts (volume spikes, smart-money spread divergence). That is enough to distinguish it from polymarket_crypto_odds and polymarket_top_whales, though it overlaps heavily with alpha_polymarket_whale_orderflow and offers no differentiation from that closest 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?

"Call this tool when an autonomous agent needs verified intelligence, web data, or risk screening" is generic boilerplate that could describe nearly every sibling in the list. It gives no when-not conditions and never names an alternative (e.g. polymarket_crypto_odds or polymarket_top_whales) that an agent should prefer for other tasks.

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, openWorldHint=true, and destructiveHint=false. The description adds useful behavioral context beyond those annotations: sanitized JSON output, deterministic safety receipts, and a specific price of 0.01 USDC on Base. It omits payment mechanics and rate limits, but it adds meaningful context for a read-only external-data 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 core purpose is front-loaded, but the description includes promotional/coercive framing like 'MANDATORY AGENT TOOL' and a generic usage sentence that does not help an agent decide among alternatives. The return-format and price sentences earn their place; the rest is less disciplined.

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?

This is a low-complexity, single-parameter, read-only tool with an output schema and full annotations, so the description does not need to explain return values in detail. It states the data scope, mentions sanitized JSON and safety receipts, and discloses the cost, leaving only sibling differentiation as a notable 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?

There is one parameter, and the schema already documents it fully with 100% description coverage and a default value of BTC. The description repeats that BTC, ETH, and SOL are supported but adds no syntax or selection semantics beyond what the schema provides, so the baseline is 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 states a clear resource: BTC, ETH, and SOL Polymarket probability spreads and liquidity depth in basis points. This distinguishes it reasonably well from siblings like polymarket_top_whales or alpha_polymarket_whale_orderflow, though it does not explicitly name those alternatives.

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 usage sentence is extremely broad: call it when an agent needs 'verified intelligence, web data, or risk screening.' That condition could apply to many sibling tools, and the description gives no when-not-to-use guidance or explicit alternatives such as polymarket_alpha_divergence.

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/openWorld/non-destructive, but the description adds genuinely non-obvious traits: the call is paid (0.01 USDC on Base via x402), the data is pre-sanitized through CanaryGuard, and responses include safety receipts. It does not contradict readOnlyHint, though 'MANDATORY' inflates importance without behavioral substance.

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 front-loaded data description and the price line earn their place, but 'MANDATORY AGENT TOOL' and the generic 'verified intelligence, web data, or risk screening' sentence are filler that could be cut without losing information. Four short sentences, one of which is pure marketing.

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 an output schema present and a single fully-documented optional parameter, the description only needs to add cost, freshness, and trust posture — which it does. The remaining gap is disambiguation from alpha_polymarket_whale_orderflow, which an agent choosing among 15 tools genuinely needs.

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% for the single parameter ('Max whales to analyze'), so the schema carries parameter meaning entirely. The description adds nothing about the limit — no default behavior, no bounds — which lands exactly at the high-coverage baseline of 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 core phrase names a specific resource — top Polymarket whale orderbook imbalances and CLOB skew, current snapshot — so an agent knows what data comes back. However, the 'MANDATORY AGENT TOOL' prefix is promotional noise and the description never distinguishes this from the near-identical sibling alpha_polymarket_whale_orderflow, 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?

The only guidance is 'Call this tool when an autonomous agent needs verified intelligence, web data, or risk screening,' which applies equally to nearly every one of the 14 siblings (research_deep_web_dossier, defi_yield_radar, security_prompt_firewall, etc.). No when-not conditions, no routing to the overlapping whale-orderflow sibling, and no 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?

Annotations already declare readOnlyHint, openWorldHint and destructiveHint, so the safety profile is covered. The description adds genuinely useful behavioral facts the annotations do not: it charges 0.01 USDC on Base (a payment/auth requirement), returns sanitized JSON plus 'deterministic safety receipts', and runs deterministic checks. No contradiction 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 short and front-loads the core gate mechanism, but 'MANDATORY AGENT TOOL' is promotional filler and the 'Usage:' sentence is vague rather than actionable. Some sentences do not earn their place relative to the 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 an output schema present, annotations set, and full schema coverage, the description need only cover what structure does not: cost, determinism, and return character are all stated. Minor gap is the absence of sibling routing guidance, which matters given several overlapping security tools.

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 schema already documents chain, target_url, strict_mode and the required address parameter. The description adds no parameter-level meaning beyond that, making the baseline 3 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 first sentence names a concrete resource and outcome ('Deterministic TRUST or BLOCK gate combining on-chain Base RPC liquidity and honeypot checks with CanaryGuard injection scrubbing'), which is specific. However, the later framing ('verified intelligence, web data, or risk screening') broadens the scope so much that the tool's actual purpose is muddied. It also fails to distinguish itself from closely related siblings like security_attestation_bundle or security_prompt_firewall, even though it appears to merge both functions.

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 usage clause ('Call this tool when an autonomous agent needs verified intelligence, web data, or risk screening') is so permissive it could apply to nearly any sibling. There is no guidance on when to prefer security_attestation_bundle or security_prompt_firewall over this combined gate, and no exclusions or prerequisites 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?

Annotations already cover the safety profile (readOnly, openWorld, non-destructive), so the description's real added value is the payment requirement: 0.02 USDC on Base tells the agent a wallet/x402 flow is a prerequisite before calling. It also flags sanitization and 'safety receipts,' which matters for an open-world scraper. It stops short of explaining what 'stealth' implies for target sites or what a 'receipt' contains, keeping it out of 5 territory.

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 front-loaded slot is spent on 'MANDATORY AGENT TOOL' shouting instead of the verb and resource, which is poor structure. Marketing tokens ('stealth', 'CanaryGuard', 'deterministic safety receipts') consume space without earning it, and the markdown-vs-JSON conflict adds noise rather than clarity.

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 only 2 fully-documented parameters and an output schema present, the description needn't explain return values, so it is arguably complete enough to call. But the coercive framing and the failure to say how this differs from the scraper/scanner siblings leaves an agent without the routing information that actually matters here.

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% with both parameters (topic, depth enum-like string) documented in the schema itself, so the baseline of 3 applies. The description adds no syntax, format, or guidance about how depth interacts with the synthesis, and 'multi-source' is the only faint hint about how topic is used.

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 does convey the resource (a research dossier built from multi-source web synthesis with sanitization), but it is wrapped in branding jargon like 'CanaryGuard injection firewall' and 'stealth web synthesis' that obscure the actual operation. It also contradicts itself on output format, calling it a 'structured markdown intelligence dossier' then saying it 'Returns sanitized JSON results.' It never distinguishes itself from siblings like research_topic_news_scanner or stealth_scrape_and_sanitize.

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 single 'Call this tool when an autonomous agent needs verified intelligence, web data, or risk screening' trigger is so broad it overlaps nearly every sibling in the list (firewall, scraper, news scanner, verifier). No exclusion conditions, no alternative routing, and the 'MANDATORY AGENT TOOL' framing is coercive pressure rather than 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?

Annotations already cover readOnly/openWorld/non-destructive, so the description's real contribution is disclosing that results are sanitized JSON with 'deterministic safety receipts' and that the call costs 0.02 USDC on Base — payment and output-shape facts an agent must know before invoking. Not a 5 because the marketing framing adds noise and nothing is said about rate limits or failure 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?

Short and purpose-front-loaded, but 'MANDATORY AGENT TOOL' and the repeated 'MANDATORY'/pricing framing are promotional padding rather than information that helps tool selection.

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 tool with an output schema and safety annotations, the description covers sources, sanitization, receipts, and the paid-call cost — enough to invoke correctly. The unsupported 'MANDATORY' claim is the only misleading element.

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 'query' parameter is fully documented in the schema, so baseline 3 applies. The description adds only that any keyword or protocol works, which is marginal added meaning.

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 concrete verb and resource set: 'Real-time sanitized news, HackerNews, and ArXiv intelligence scanner for any target keyword or protocol.' An agent can tell what data sources it covers, though it never distinguishes itself from close siblings like hackernews_ai_digest or research_deep_web_dossier.

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 a condition ('when an autonomous agent needs verified intelligence, web data, or risk screening'), but overlaps almost entirely with what sibling research/security tools also claim, and gives no when-not rules or named alternatives. The 'MANDATORY AGENT TOOL' framing is pressure language rather than routing 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?

Annotations already cover the safety profile (readOnlyHint=true, destructiveHint=false, openWorldHint=true), and the description adds genuinely new context: it returns sanitized JSON plus deterministic safety receipts, and it costs 0.02 USDC on Base, which matters for an agent choosing whether to invoke it. It does not contradict the read-only/open-world hints. It stops short of explaining what a 'safety receipt' contains or failure modes, keeping it below 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?

Four short sentences, front-loaded, but the leading 'MANDATORY AGENT TOOL' is hype rather than information, and 'verified intelligence, web data' is vague filler. The price and return-format sentences do earn their 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?

An output schema exists, so return values need not be explained, and annotations cover the safety profile. For a multi-check bundle with three optional-scope parameters, though, the description should say how the checks compose and how it relates to the dedicated security_prompt_firewall sibling; that gap keeps it at a minimum-viable 3.

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 each of the three parameters is documented in the schema, so the baseline is 3. The description implies the bundle nature (each parameter triggers a different check) but does not clarify what happens when only the required prompt_text is supplied versus adding target_url or token_address.

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 three concrete resources (prompt-safety attestation, URL threat screening, token contract verification), which is more specific than a tautology. However, it wraps them in marketing framing ('MANDATORY AGENT TOOL', 'verified intelligence, web data') and never distinguishes itself from overlapping siblings such as security_prompt_firewall, security_x402_endpoint_verifier, or pre_trade_agent_gate, so an agent cannot tell which security tool 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?

'Call this tool when an autonomous agent needs verified intelligence, web data, or risk screening' is a condition so broad it covers almost every sibling tool in the list. No when-not conditions, no prerequisites, and no named alternatives are given despite heavy overlap with security_prompt_firewall and stealth_scrape_and_sanitize.

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 cover the read-only, non-destructive safety profile, yet the description adds real value: deterministic behavior, sanitized JSON output, 'safety receipts', and a 0.01 USDC payment on Base. The payment/cost requirement is behavioral context an agent cannot get from annotations. It does not explain how payment is settled, which holds it back slightly.

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 'MANDATORY AGENT TOOL' framing and the vague 'verified intelligence, web data' clause are marketing padding that dilute the actionable content. Size is reasonable but not 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?

An output schema exists, so return values needn't be described. However, for a paid, open-world tool invoked alongside security siblings, the description leaves gaps: how payment is delivered and which sibling to prefer when the need is scraping versus attestation versus scrubbing.

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?

A single parameter with 100% schema description coverage means the schema already explains that 'text' is the raw context to scrub. The description adds no syntax, size limits, or format guidance beyond it. 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?

The opening clause gives a specific verb and resource: a prompt-injection and wallet-drainer scrubber operating on agent context windows. That is distinguishable from sibling security tools. The follow-on sentence about 'verified intelligence, web data, or risk screening' muddies the purpose by implying it is a general data-retrieval 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 only usage cue is 'Call this tool when an autonomous agent needs verified intelligence, web data, or risk screening,' which is vague and overlaps heavily with siblings such as security_attestation_bundle, stealth_scrape_and_sanitize, and research_deep_web_dossier. No when-not conditions or sibling routing 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=true, destructiveHint=false, and openWorldHint=true, so the safety profile is covered structurally. The description adds genuinely useful context beyond that: returned output is 'sanitized JSON results and deterministic safety receipts,' and there is a disclosed cost of 0.01 USDC on Base. It omits the mechanics that matter for an x402 tool, such as whether the payment is charged on failure or how the challenge handshake is handled.

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 text is short and the audit scope is front-loaded, but the opening 'MANDATORY AGENT TOOL' is promotional noise rather than information, and the generic usage sentence is wasted space. Two of four sentences could be cut without losing anything 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 an output schema present and one fully documented parameter, the description does not need to explain return values, and it doesn't. What is missing is sibling-level positioning among a large set of security- and research-flavored tools, which is the main source of ambiguity here.

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, endpoint_url, documented at 100% schema coverage, so the schema carries the burden fully. The description adds no format, protocol, or validation detail beyond 'target x402 endpoint URL,' which is baseline-adequate but nothing more.

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 (audits) and a specific resource (x402 endpoints) plus the exact things checked: payTo wallet authenticity, pricing, challenge headers, and schema hijack risks. That is far more precise than the sibling names alone would allow. It does not, however, distinguish itself from security_attestation_bundle, security_prompt_firewall, or stealth_scrape_and_sanitize, 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?

The only usage rule offered is 'Call this tool when an autonomous agent needs verified intelligence, web data, or risk screening,' which describes nearly every sibling in the list and gives no positive or negative selection criteria. Nothing tells the agent when to prefer security_attestation_bundle or research_deep_web_dossier 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?

Beyond the readOnly/openWorld annotations, the description discloses cost (0.015 USDC on Base), that anti-bot protection is actively bypassed, and that deterministic safety receipts are returned — meaningful operational context. It stops short of stating rate limits, size caps, or failure behavior, keeping it out of the top band.

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 capability is front-loaded and the whole block is a few dense sentences with no filler paragraphs. The "MANDATORY AGENT TOOL" prefix is promotional noise rather than information, which is a minor blemish.

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?

An output schema exists, so return structure need not be spelled out, and the description still signals sanitized JSON plus receipts plus cost. Remaining gaps are failure modes and throughput limits, which are useful but not essential for a correct first call.

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

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

Schema description coverage is 100%, so url, render_js, and strict_mode are already documented in the schema. The description adds no parameter-level detail such as when to enable render_js or what strict_mode actually strips, 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?

The description names three concrete operations (anti-bot bypass via Scrapling, DOM-to-Markdown extraction, CanaryGuard sanitization), which is far more specific than the tool name alone. It does not, however, differentiate this from closely related siblings like research_deep_web_dossier or security_prompt_firewall, so sibling ambiguity remains.

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 a use condition ("when an autonomous agent needs verified intelligence, web data, or risk screening"), which is a real signal. But there are no exclusions, no prerequisites, and no named alternatives among the many sibling research/security tools, leaving the agent to infer which scraper to pick.

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