HirePulse Commerce Research

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

Annotations already declare readOnlyHint and openWorldHint, and the description adds important behavioral context beyond them: the cost is $0.02 per comparison, only one product is sampled per store, and unavailable evidence remains unknown. These details materially affect whether and how an agent should invoke the tool.

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

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

The description is front-loaded with the tool's purpose, then adds cost, appropriate-use routing, and a sampling caveat. Every sentence contributes operational information without repetition or filler.

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

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

Given the full schema coverage, existing output schema, and annotations covering read-only and open-world behavior, the description is complete enough to call the tool correctly. It covers output dimensions indirectly, sampling limitations, cost, and alternative 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 the domain, competitor_domains, and context parameters thoroughly. The description reinforces that competitors are capped at three and that one product is sampled per store, but it does not add syntax or constraints 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 states a specific verb and resource: it compares a brand against up to three competitor store domains as a shopping schema covering prices, ratings, availability, shipping, and returns. It also distinguishes itself from named sibling tools, so an agent can identify its role without opening schemas.

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 explicitly says to use this tool for a bounded cross-store comparison and names alternatives: universal_product_url_to_json for one product and muse_agentic_store_readiness_auditor for a single-store discovery audit. This gives clear when-to-use and when-to-use-something-else 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 only declare readOnlyHint and openWorldHint; the description adds the crucial behavioral fact that the returned request is a preview and is not executed, plus that the advisor is free and that sample_domain draws on cached hints without running a new lookup. Those are exactly the traits an agent needs to avoid assuming a side effect.

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 the capability, then the routing rule, then the non-execution caveat. Every sentence carries distinct information with no repetition of the title.

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 shape need not be explained; the description covers what is returned conceptually (tool, price, balance, request preview). With annotations, full schema coverage, and only one required parameter, an agent has everything needed to call it correctly.

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

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

Schema description coverage is 100% and all four parameters are documented there, so the baseline is 3. The description reinforces the intent (goal → tool + price estimate) but adds no format, syntax, or range detail beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource — a free advisor that maps a stated goal to the matching HirePulse tool along with price, free-call balance, and a ready-to-run request — and enumerates the goal categories it handles. It explicitly separates itself from the sibling get_company_profile, so an agent can pick between them without opening schemas.

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

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

Gives an explicit use condition ("when the right tool or expected cost is unclear") and an explicit alternative with its own condition ("go directly to get_company_profile for a known domain and a full company brief"). Nothing is left to inference about routing.

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

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

Beyond the readOnlyHint and openWorldHint annotations, the description discloses the critical caveat that codes are not verified at checkout, identifies the data source as homepage metadata, and states the pricing model of $0.01 per non-empty result. It also clarifies what the tool will not do (apply coupons or place an order), which is exactly the kind of behavioral context an agent needs before calling it.

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 four tight sentences with no wasted language. Critical caveats (unverified codes, pricing) and routing guidance are front-loaded and easy to scan.

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

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

Given the output schema exists, the description need not explain return values. It still covers the essential context: source of the codes, lack of checkout verification, cost per non-empty result, intended usage, alternative tool, and explicit non-actions.

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 domain, context, and product_category parameters are already well documented in the schema. The description adds general context about the domain being a shop's homepage metadata, but does not add parameter-specific syntax or constraints beyond what the schema provides.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific resource (coupon code candidates), a specific source (homepage metadata of a shop), and the accompanying source text. It also explicitly distinguishes the tool from adjacent capabilities by saying it does not apply coupons or place an order and by pointing to universal_product_url_to_json for product prices and availability.

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 clear use case (collect possible discounts before checkout), names the alternative tool for product prices and availability, and states the key exclusion (does not apply coupons or place an order). It also warns that codes are not verified at checkout, which directly shapes when the result should be trusted.

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 annotations, it discloses the key behavioral traits an agent needs: one-time use, 25 successful calls, any single tool, not tied to IP, valid 30 days, and where to place the returned token. The readOnlyHint=false annotation is consistent with a claim action, and the description adds substantial operational context.

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 dense sentences, front-loaded with the core offer, followed by the input rule and token-passing mechanics. Every sentence carries actionable information with no waste.

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 claim tool with no output schema, the description covers what the trial provides, the mutually exclusive input rule, and how to use the token afterward. Nothing essential for calling it correctly 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 coverage is 100%, but the description adds a constraint not expressed in the schema: submit exactly one of email or wallet. It also clarifies that no email is sent and how the resulting token is passed via params._meta or the X-Trial-Token header, which is valuable semantic guidance beyond the field 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 states a precise verb and resource: claim a one-time trial pass of 25 free successful calls. It specifies scope (any single tool), duration (30 days), and non-IP binding, so an agent can tell exactly what the tool offers without opening the schema.

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

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

It gives a clear usage condition (claim a one-time trial) and an explicit input constraint: send exactly one of a Base wallet or a work email. It does not name when not to call it or any alternative path, but there is no obvious sibling alternative among the listed 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 declare readOnlyHint and openWorldHint, and the description reinforces non-mutation ("Does not modify the store") while adding genuinely new context: a per-result price ($0.01), the heuristic (non-authoritative) nature of the score, and an explicit scope exclusion of certification/checkout testing. It stops short of describing latency, failure modes, or what happens with an unreachable domain, so it is strong but not exhaustive.

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 dense sentences, front-loaded with what is audited, then boundaries, price, and alternatives. No filler sentences, though the opening clause stacks several audit dimensions and reads more like a spec list than prose.

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 fills most remaining gaps: cost, heuristic caveat, sibling routing, and non-mutation. The only omission is operational behavior on edge cases (invalid or unreachable domains) which an agent might want before spending $0.01.

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 both parameters are documented there, including the domain format constraint (no scheme/path/port) and the optional context field. The description adds no parameter-level meaning, so the baseline 3 applies; the schema does the heavy lifting.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource ("Store audit") and enumerates the exact dimensions checked: machine-readable product data, UCP/ACP discovery, payment hints, robots.txt access, plus a heuristic score and prioritized fixes. It is immediately distinguishable from the product-level and trust-check siblings, which it names 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?

Gives the positive case ("Use to diagnose agent-readable store discovery and prioritize fixes") and routes to two concrete alternatives with the conditions that select them (universal_product_url_to_json for one product, pre_purchase_merchant_trust_check for purchase-risk evidence). It also states a negative boundary: "Not a certification or checkout test."

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?

Adds real context beyond the readOnly/openWorld annotations: the qualification rule (needs both ad and SEO evidence), the caveat that public emails are unverified decision makers, and a $0.05 per qualified result cost. That pricing and evidence-gating is exactly the kind of disclosure annotations cannot carry. It stops short of saying anything about latency, result shape, or what happens when a store fails qualification.

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?

Dense but every clause carries information — criteria, caveat, price, alternatives, exclusions. The opening semicolon-chained sentence is somewhat awkward to parse, but the routing guidance is clearly front-loaded in the second half.

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 no explanation. With cost, qualification criteria, data caveats, exclusions, and sibling routing all present, an agent has everything needed to decide whether to call it and what to expect.

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 both parameters are fully documented in the schema, so the baseline applies. The description only implies that 'domain' identifies the known store and adds nothing about format or the context parameter.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (qualify a store as a lead) plus the required evidence (ad activity and SEO/schema-gap signals), which is far more than a restatement of the name. An agent can distinguish this from the readiness auditor and the contacts extractor without opening any schema.

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

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

Names two explicit alternatives with the condition that selects each: muse_agentic_store_readiness_auditor for an audit without lead qualification, extract_company_contacts for contacts only. It also scopes usage to 'a known store' and excludes outreach and conversion-loss measurement.

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, and the description adds real value beyond them: it discloses pricing ($0.005 after shared free calls) and the critical caveat that it cannot certify safety. It stops short of describing evidence sources or how the score is computed, so it is strong but not exhaustive.

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?

Sentences are dense but each carries load: scope, limits, price, alternative, and boundary are all front-loaded. The 'x402 API endpoints: x402_merchant_trust_check' fragment is the one piece that adds ambiguity rather than clarity, since it collides with an actual sibling tool name.

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

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

With an output schema present and annotations covering the safety profile, the description only needed to add scope, cost and caveats — which it does. The remaining gap is the confusing reference to an 'x402 endpoint' that shares a name with a sibling tool, which could make an agent question whether it is calling the right one.

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 each parameter (domain, context, merchant_wallet_or_id, transaction_amount_usd) already carries its own description. The description adds no format or interpretation guidance beyond restating that the call does not authorize a purchase, which the schema already says — 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 the specific resource (public trust evidence for an unfamiliar online shop) and enumerates exactly what the tool returns: evidence score, risk flags, missing signals and limits. It also distinguishes itself from b2b_vendor_stability_evaluator, so an agent can differentiate it from siblings without inspecting schemas.

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 an explicit positive condition (consumer purchase from an unfamiliar shop) and an explicit alternative for the other case (B2B supplier procurement → b2b_vendor_stability_evaluator). It also states a hard boundary: it does not buy goods or authorize payment.

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 and openWorldHint=true, so the safety profile is covered. The description adds genuinely useful behavior beyond that: no browser required, multi-format extraction fallback chain, missing facts returned as null, and a $0.002 per-result cost. The cost and null semantics are meaningful additions, but return shape and fetch-failure behavior are left to the output schema.

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

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

Two sentences, front-loaded with what is extracted and from where, then the routing/guardrail sentence. No filler and nothing repeated from the title.

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 described. Between the extraction sources, null-on-missing behavior, per-result pricing, and the named alternatives, an agent has everything needed to decide and invoke correctly.

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

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

Schema description coverage is 100%, so both parameters are already documented in the schema; the baseline of 3 applies. The description reinforces the single-URL, product-detail-page constraint (not a homepage, not a batch), which is a mild addition over the schema rather than new syntax or format guidance.

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?

Specific verb+resource ('Product page to JSON') with the exact fields extracted (price, stock, variants, ratings, shipping) and the extraction sources named. It also distinguishes itself from the two nearest siblings by name, so an agent can route without opening any schema.

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

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

States the positive case explicitly ('Use for one product detail URL') and then names two concrete alternatives with the conditions that select them: cross-store comparison and store-wide discovery audit. When-to-use and when-not-to-use are both covered.

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 adds substantial behavior beyond the annotations: it says scripts, navigation, and ads are removed; title, meta description, and token estimate are included; truncation is marked; and pricing is $0.002 with empty results free. These details are highly useful for an agent deciding whether and how to call the tool.

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

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

The description is a single dense sentence that front-loads the core operation and then adds the most decision-relevant constraints: output cleanliness, max_chars range, and cost. Every clause carries useful information.

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

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

Given 100% schema coverage, an output schema, and annotations covering read-only/open-world behavior, the description supplies the remaining decision-critical context: public-page scope, cleaning behavior, truncation, token estimate, and pricing. An agent has enough information to call it correctly.

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

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

Schema description coverage is 100%, so the schema already documents url, context, and max_chars thoroughly. The description restates max_chars bounds and default and adds the pricing note, but it does not add parameter meaning beyond what the schema provides; baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states that it converts a public web page into clean Markdown, including title, meta description, and token estimate, while removing scripts, navigation, and ads. It is specific about the operation and output traits, but it does not distinguish itself from possible sibling URL-conversion tools such as universal_product_url_to_json.

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 word 'Public' implies that private pages are out of scope, and the pricing note helps frame usage economics. However, there is no explicit when-to-use guidance, no stated alternatives, and no when-not-to-use conditions beyond the public-page constraint.

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 annotations only declare readOnlyHint and openWorldHint, while the description adds important behavior: pricing at $0.005 per result, a signed artifact with expiry and a public verification key, and scope limitations such as proving HirePulse issuance but not ownership or purchase safety. There is no contradiction with 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?

The description is compact and front-loaded with the artifact definition and its key limitation. Every sentence adds useful information: provenance, price, usage routing, and exclusion.

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 output schema, annotations, and full schema coverage, the description supplies the remaining decision-critical details: cost, what the badge proves and does not prove, and when to choose sibling tools. An agent has enough information to select and invoke this tool correctly.

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

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

Schema description coverage is 100%, and both parameters are already well documented in the input schema. The description does not add parameter-level semantics beyond what the schema provides, so the baseline score of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific artifact and resource: a signed public-evidence statement for a merchant domain, including expiry and a public verification key. It also explicitly distinguishes this from pre_purchase_merchant_trust_check and x402_merchant_trust_check, and clarifies what the badge proves versus what it does not prove.

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 explicit when-to-use guidance ('Use when you need a portable signed assessment') and names two alternatives with their selecting conditions: pre_purchase_merchant_trust_check for risk evidence without a badge, and x402_merchant_trust_check for an API endpoint. It also states an exclusion: it does not issue a third-party certification.

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 only give readOnlyHint and openWorldHint; the description adds material context beyond them: a per-call price, a free-on-unreachable pricing exception, an explicit epistemic caveat ('Heuristic, not a guarantee'), and the assurance that the scan does not itself authorize payment. These are exactly the traits an agent needs before spending money on a scan.

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, all load-bearing, with the scope constraint and price front-loaded before the sibling routing. The first sentence is a heavy enumeration, but each listed check maps to a real capability rather than padding.

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

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

Output shape is covered by the output schema, so the description only needs to convey purpose, cost, limits, and alternatives — all present. An agent can decide, pay for, and interpret this call without opening anything else.

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

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

Schema description coverage is 100%, so target_url and context are already documented in the schema, and the description adds no syntax, format, or constraint detail beyond them. Baseline 3 applies because 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 and resource ('Pre-payment check of an x402 API endpoint') and enumerates exactly what is inspected: discovery files, live 402 terms, USDC prices, latency, prompt-injection flags, and CDP Bazaar statistics. It explicitly distinguishes itself from the closest sibling by routing online shops to pre_purchase_merchant_trust_check.

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 anchored to a concrete decision point ('before signing a payment authorization'), with an explicit alternative named for the adjacent use case ('Online shops: pre_purchase_merchant_trust_check'). The cost/refund rule ('$0.002; unreachable targets are free') further informs the call decision.

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