ghost-x402-market-intel-vet-schema

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

With zero annotations, the description carries the full burden and does so: it discloses the exact price ($0.01 USDC on Base), that payment 'settled before the tool runs' (i.e., you pay even if results are poor), a free preflight with a 3/day cap, spend-limit settings, and an honest caveat that funded delivery through x402-proxy is unverified. These are exactly the consequential traits an agent cannot get from schema or 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 front-loaded with purpose and triggers, but roughly half the text is payment plumbing (x402, spendLimitPerTx, /llms.txt pointer) that sits awkwardly in a tool description, and the reuse-until-expiry rule is stated twice (in the trigger sentence and again after the return contract). Every element is relevant, but the block is denser and longer than a caller skimming for 'what does this do' 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?

There is no output schema, so the description must describe returns — and it does, naming the verdict enum, the exact call, a fallback, valid_until and recheck_when. Pricing, payment mechanics and the preflight path are covered. The remaining gap is failure behavior: it never says what the caller gets (or is charged) when no provider matches the filters.

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 86%, so the baseline is 3, and the description adds selective meaning on top: 'by need' maps to the free-text query, the ranking evidence (independent payers, calls-per-payer, last settlement) explains why min_payers and price filters exist, and the payment_signature two-step flow is restated coherently. It does not clarify limit/pagination semantics or what a zero-result search with filters returns, so it stays short of a 5.

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 concrete verb+resource pair: it 'finds providers by need and ranks them by real economic evidence' and returns USE/WATCH/AVOID verdicts. That is clearly distinguishable from the vetting/forecasting siblings, though it never names ghost_commerce_vet or explains the split between searching for providers versus vetting a known one. The opening line is a decision-oriented aphorism rather than a statement of function, pushing the actual purpose to the third sentence.

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 enumerates explicit invocation triggers — provider unknown, a held decision past valid_until, or a material change in price/health/verdict/funding — and pairs them with a negative rule: reuse a held decision until it expires or a trigger fires rather than asking again. That is precise when-to-use and when-not-to-use guidance in one place, with no inference required.

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

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

With no annotations, the description carries the full burden and does so well: it discloses the paid x402 model, price and settlement timing, spend-limit guidance, verdict semantics, what PROCEED means, what is reported under `evidence` and `unresolved`, the limitation that Ghost does not verify seller identity or delivery, and the important caveat that x402-proxy payment/delivery is not yet verified.

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 purpose and scenario, and most of its length is justified by payment mechanics and caveats. However, it has some redundancy, notably 'Paid per call via x402' followed immediately by 'Payment: $0.01 USDC on Base per call over x402.'

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 tool with no annotations and no output schema, the description is substantial: it explains the verdicts, evidence categories, unresolved issues, payment flow, and critical limitations. It could be more complete by defining CAUTION, REJECT, and INSUFFICIENT_EVIDENCE and the signed receipt format, but it is sufficient to invoke the 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 the schema already clearly documents `address`, `endpoint_url`, `advertised_amount`, and `payment_signature`. The description reinforces the address/endpoint and quote-vs-advertised price concepts but adds no new syntax, format, or edge-case guidance beyond the schema.

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

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

The description clearly identifies the tool as pre-payment seller due diligence, listing the specific checks it performs (settlement history, payer structure, funding links, endpoint liveness, quote-vs-advertised price) and the verdicts it returns. It does not explicitly name sibling tools, so it stops short of full sibling differentiation.

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: 'Use when one named provider or payment address is already in hand and you need a verdict before you pay it.' That effectively distinguishes the scenario from broader search, but it does not explicitly list when not to use it or name alternative tools.

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

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

With no annotations, the description carries the full behavioral burden and does so in detail: decision outputs, x402 pricing and settlement, prepaid credit/cache behavior, INSUFFICIENT_EVIDENCE handling, spend-limit setup, and an explicit unverified-delivery caveat. This is exactly the context an agent needs for a payment-affecting 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 purpose and decision outputs are front-loaded, and most sentences carry useful operational detail. The payment/x402-proxy wording is lengthy, though largely justified for a payment gate.

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

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

For a complex tool with no annotations and no output schema, the description explains the decision statuses, economics logic, payment path, and outcome-reporting loop. It does not fully specify the response shape or all input semantics, leaving some gaps.

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 only 36% across 14 parameters, so the description must compensate. It lists key economic inputs and reinforces that unknown values stay UNKNOWN, but it does not define most fields or explain the provider-candidate structure, so it only partially fills the gap.

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 operation: a pre-spend gate called immediately before paying an x402/API provider, returning one of four explicit decisions. It clearly distinguishes this from ranking/search logic and is unambiguous against the sibling search/vet tools even without naming them.

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

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

It gives explicit timing guidance ('Call this immediately before your agent pays') and explains the decision context. It does not name sibling alternatives or state when-not-to-use cases, keeping it below a 5.

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

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

With no annotations, the description carries the burden and does well: it discloses per-call cost ($0.01 USDC on Base via x402), that payment settles before execution, that a DSSE-signed receipt is returned, and required client spend-limit setup. It even flags that funded payment/delivery through x402-proxy is unverified, which is unusually honest. It doesn't describe the response payload structure, keeping it just 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?

The leading question is a strong front-loaded hook, followed by the usage trigger and then payment terms. It is somewhat dense and the payment paragraph partially duplicates the schema field text, but every sentence carries operational information and none is 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 three simple params, full schema coverage, and no output schema, the description supplies the missing pieces an agent needs: cost, payment mechanics, prerequisite configuration, and the semantic shape of the answer (changed vs unchanged since a fingerprint). Only the concrete return payload of the DSSE receipt is left undescribed.

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 all three params (url, known_fingerprint, payment_signature) are already documented. The description only restates the payment flow that the payment_signature schema field already explains, adding no format or value semantics 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?

Opens with a specific verb+resource: checks whether a published JSON Schema or OpenAPI document has changed since a held fingerprint. This is a distinct capability from the sibling commerce search/vet/gate tools, so an agent can route to it 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?

Explicitly frames the tool as 'the schema-drift recheck of the pre-spend policy' and says to run it 'when a provider's published contract may have moved before you pay it again,' which gives a concrete trigger condition. It stops short of naming ghost_pre_spend_gate as the alternative or saying when not to use it, but the context is clear.

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

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

With no annotations present, the description carries the full burden and does so unusually well: exact price and chain ($0.01 USDC on Base via x402), settlement ordering (paid before the search runs), failover path (Serping → Serper) with its retry cost, and the failure-refund behavior (fee becomes Ghost service credit, not an on-chain refund). It also bounds the DSSE receipt's meaning — it proves what was returned and by which upstream, not accuracy or currency — and flags that a funded payment path via x402-proxy is unverified.

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

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

Front-loaded with purpose before payment mechanics and caveats, which is the right order for a paid tool. It is on the long side and repeats the payment point ('ONE payment' up front, then a full Payment paragraph, then 'there is no second payment'), which costs some density but each block is informative rather than filler.

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

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

No output schema exists, but the description describes the return shape (normalised organic hits plus answer box, knowledge panel, related questions) and the receipt artifact, covering what an agent needs to interpret results. Combined with the cost, failure-mode and refund disclosures, nothing material is missing for correct invocation.

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

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

Schema description coverage is 100%, so query, country, language, results and payment_signature are already documented in the schema, which sets the baseline at 3. The description adds context about payment timing but nothing extra about the search-shaping parameters (e.g., how country/language interact or what 'results' counts).

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 ('Search the web and get the results') and enumerates the returned payload (organic hits with title/url/snippet, answer box, knowledge panel, related questions). It also scopes negatively ('Search only: Ghost does not fetch the pages'). However, it never names or contrasts the sibling tools (ghost_commerce_search, ghost_commerce_vet), so an agent must infer the boundary from names alone.

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?

Clear usage context: one call performs one paid search, the payment is settled before the search runs, and clients like x402-proxy pay automatically while others must pass payment_signature. It also warns to set spendLimitPerTx/spendLimitDaily before use. It stops short of explicit when-to-use-this-vs-ghost_commerce_search routing, so 4 rather than 5.

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