402oracle

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

With no annotations provided, the description carries full transparency burden. It discloses the output (signed attestation, 0-100 trust score, evidence URLs), behavioral differences between free (unsigned, rate-limited) and paid tiers (signed, $0.05 USDC via x402), and notes audit suitability. This is comprehensive for a verification 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 primary purpose and use cases. It consists of four sentences, each adding substantive information (checks, return value, pricing/tier differences). No filler, though it is slightly dense with multiple details packed into the final sentence.

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 a single parameter, no annotations, and no output schema, the description is remarkably complete: it specifies what checks are performed, what the return value includes (trust score, evidence URLs, signing), and pricing/rate-limit trade-offs. This is sufficient for an agent to select and 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?

The schema has 100% coverage for the single 'domain' parameter. The description adds meaning by explaining that the domain is used for RDAP, DNS, email posture, and HTTPS checks, which helps the agent understand what kinds of values are appropriate. This goes beyond the schema's basic example.

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

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

The description uses a specific verb 'Verify' with a clear resource ('a business or domain'), states the goal ('is real and established'), and enumerates concrete checks (RDAP, DNS, email posture, HTTPS reachability). This clearly distinguishes it from sibling tools like verify_claim, verify_freshness, and verify_price.

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

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

The description explicitly states when to use the tool: 'before your agent pays an invoice, onboards a vendor, or trusts it'. It does not explicitly name alternatives or state when not to use it, but the distinct purpose makes the use context clear. The free vs paid tier guidance also adds actionable context.

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 provided, the description carries the full burden and does well: it discloses the output (verdict, confidence, citations), the signed attestation, the free tier's unsigned and rate-limited nature, and the paid HTTP endpoint with cost and signing. It does not explicitly state that it is read-only, but that is implied by 'fact-check' and not contradicted by any 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 three sentences long, front-loaded with the purpose, then behavioral details, then pricing/auth. All sentences provide relevant information, but the third sentence about endpoint and pricing is somewhat detailed and could be condensed. It is not bloated, but not maximally concise.

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 simple one-parameter tool with no output schema, the description covers purpose, output format, and access tiers well. It lacks explicit caveats about error conditions or length limits, but those are partially in the schema. Overall, sufficient for an agent to select and 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?

The schema covers 100% of the single parameter ('claim') with a clear description. The tool description reiterates 'single factual claim' but adds no additional semantic detail (e.g., examples, formatting, edge cases). Baseline 3 is appropriate since 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?

The description begins with an explicit verb and resource: 'Fact-check a single factual claim against web evidence.' It clearly distinguishes this from sibling verification tools (verify_business, verify_freshness, verify_price) by focusing on factual claims and calling itself a 'hallucination guard.'

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

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

The description says 'before your agent relies on it,' which gives clear context for when to use the tool. It also implies it is for preventing hallucination. However, it does not explicitly state when not to use it or name alternatives (e.g., use verify_price for price checks), so it misses the 'explicit exclusions' threshold.

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 provided, the description carries the full burden of behavioral disclosure. It explicitly lists the return data (HTTP status, Last-Modified/ETag, content SHA-256, changed flag, signed attestation) and explains the free vs. paid tier behaviors (unsigned/rate-limited vs. cryptographically signed). This is highly transparent and goes beyond what the structured schema provides.

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 concise and well-structured: the first sentence states the core purpose, the second enumerates the return values, and the third explains the tiers and pricing. Every sentence adds value with no redundancy 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 tool's moderate complexity, the description covers the essential aspects: purpose, usage timing, return data, and tier differences. It does not explicitly mention error handling or edge cases (e.g., unreachable URL), but the listing of HTTP status implies that. With no output schema, the description's list of return fields is sufficient for most use cases. Slight lack of detail on failure modes prevents a 5.

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

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

The input schema already describes both parameters with 100% coverage ('Full URL including https://' and 'Optional prior SHA-256 hex to compare against'). The description adds minimal extra meaning—it implies the prior hash is used for change detection—but does not significantly enrich parameter understanding. Per the baseline for high schema coverage, a 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 the tool's function: 'Check that a URL is live and its data is fresh before your agent acts on its contents.' It specifies the resource (URL) and the action (verify freshness), and distinguishes from sibling tools (verify_business, verify_claim, verify_price) by focusing on URL content freshness and returning specific HTTP and content metadata.

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

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

The description provides a clear usage context: 'before your agent acts on its contents.' It also distinguishes between free (unsigned, rate-limited) and paid ($0.02 USDC via x402) tiers, giving practical guidance on when each is suitable. However, it does not explicitly state when not to use this tool or name alternative tools, so it falls short of 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 provided, the description carries full burden and succeeds: it discloses the cross-checking of Coinbase/Kraken/OKX, median calculation, divergence flagging, and the signed attestation output. It also provides honest details about the free tier being unsigned and rate-limited, and the paid tier's cost and endpoint.

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 main purpose, followed by mechanism, output, and pricing details. Every sentence adds value: purpose, oracle method, attestation, and tier differences. There is no fluff or redundancy, making it appropriately sized for the complexity.

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

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

Given the tool's moderate complexity (multi-exchange aggregation, signed attestation, tiered access), the description covers the key aspects: what it does, how it aggregates, output type, and free/paid distinction. It lacks explicit return format details, but no output schema exists, so some description of the attestation structure could be helpful. Still, it is quite complete for a one-parameter 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 for the single 'symbol' parameter is 100% with a clear description ('Ticker symbol, e.g. BTC, ETH, SOL'). The tool description does not add extra parameter-level semantics beyond what the schema provides, but no additional info is needed. The baseline of 3 is appropriate when schema covers everything.

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

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

The description clearly states the tool's purpose: 'Confirm a crypto asset's price before your agent trades, quotes, or settles on it.' This uses a specific verb and resource, and the scope is unambiguous. It distinguishes itself from sibling tools (verify_business, verify_claim, verify_freshness) by focusing exclusively on price verification.

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

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

The description gives clear contexts for use ('before your agent trades, quotes, or settles on it') and explains the free vs. paid tiers. However, it does not explicitly mention when NOT to use this tool or name alternative verification approaches, though the sibling list implies alternatives for non-price verification.

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