402oracle

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: it discloses the exact evidence gathered (RDAP domain age/registrar, DNS A/MX/NS, SPF/DMARC, HTTPS), the return shape (verdict plus 0-100 trust score with evidence URLs), the flagged risk pattern, and the operational constraints (free tier unsigned and rate-limited, $0.05 USDC for signed/no-limit, payment header names, transport parity).

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 the core question and purpose, and most sentences earn their place. Some redundancy exists: the standalone fragment 'Signed attestation.' plus the later full signed-attestation/payment paragraph and 'Same price on either transport' overlap slightly, costing some tightness.

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, and the description compensates by describing the verdict, trust score range and evidence URLs returned. Combined with the payment/auth tiering and rate-limit notes, an agent has everything needed to call this correctly in a single domain argument.

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?

Only one parameter and the schema already documents it at 100% coverage ('Domain to verify, e.g. example.com'). The description never adds domain-specific syntax (subdomains, IDN, scheme handling) beyond what the schema states, so the baseline of 3 applies.

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

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

States a specific verb and resource ('Is this company or domain legit? Business and domain verification (KYB)') with concrete scope: vendor screening, supplier checks, scam/fraud review. This is clearly distinct from the sibling tools verify_claim, verify_freshness and verify_price, so an agent can route correctly 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?

Gives explicit triggering moments ('Use it before your agent pays an invoice, onboards a vendor or trusts a site') and names alternatives for adjacent needs: the batch endpoint for bulk and the paid x402/HTTP path for signed attestations. When-to-use and the alternative paths are both spelled out.

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 of behavioral disclosure. It explains the tool's rate-limiting on the free tier, the optional payment for no daily limit, and the signed vs. unsigned attestation behavior. This is more than typical, though it doesn't detail what happens on invalid input or network failures, but the essential behavior is well covered.

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 paragraph that is information-dense but not bloated. It front-loads the core purpose and then expands on features and payment options. The length is justified by the complexity of the signing and payment details, and every sentence serves a purpose, though it could be slightly more structured for readability.

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, complete schema coverage, no output schema, and no annotations, the description is thorough. It covers the tool's function, outputs, signing mechanism, rate limits, and payment alternatives. It misses only minor details like error handling or response format specifics, but overall it provides sufficient context for an agent 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?

The schema covers the claim parameter with a character length constraint, but the description adds important context: it clarifies that the claim must be factual and single, and it explains the significance of the claim in the fact-checking process. With 100% schema coverage, a baseline of 3 is expected, but the description elevates it by hinting at the claim's role in the verdict.

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: fact-checking a claim against live web evidence, with specific outputs (verdict, confidence, citations) and a signing mechanism. It distinguishes itself from sibling tools by focusing on general claims rather than business, freshness, or 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 explicitly explains when to use the tool (before relying on a claim, for misinformation review, as a hallucination guard) and provides guidance on alternatives (free vs. paid tiers, different transport methods). It also mentions alternatives like POST /verify/claim, ensuring the agent knows the options.

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 delivers: it enumerates the exact returned signals (status, Last-Modified, ETag, SHA-256 fingerprint, changed-vs-prior-hash), discloses that free-tier responses are unsigned and rate-limited, explains how to obtain a signed attestation, and states the price and transport options.

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 and the four use cases are front-loaded in the first two sentences. The payment and transport boilerplate at the end is relevant to correct invocation but is dense; the definition is longer than strictly necessary yet every sentence carries 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?

With no annotations and no output schema, the description compensates by fully describing the return payload and the paid-vs-free behavioral difference. An agent has everything needed to call the tool and interpret its output without additional fields.

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%, so the baseline is 3, but the description adds real meaning beyond the schema: it clarifies that prior_hash is compared against the newly computed content fingerprint to yield the 'changed' verdict, turning an opaque field into a purposeful input.

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: fetch a URL and report uptime plus content change (HTTP status, Last-Modified, ETag, SHA-256 fingerprint). It is clearly distinguished from siblings verify_business, verify_claim, and verify_price, which verify different resources entirely.

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 concrete usage scenarios — check a site is live, detect stale data, monitor a page, or decide whether to invalidate a cache before acting on the content. It does not explicitly state when NOT to use it or name alternative tools, but the sibling set targets unrelated resources so the routing risk is low.

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 delivers: it discloses the 2-live-quote minimum, that unlisted tickers are not charged, the free tier's unsigned/rate-limited nature, and the x402 payment mechanics with exact header names and cost. This is unusually rich behavioral detail for a tool with zero annotation coverage.

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 the core purpose and usage triggers, and the pricing/transport details follow logically. It is dense but every sentence (exchange list, spread/flag output, quote minimum, free-vs-paid, headers) serves a decision. Slightly long, keeping it from a 5.

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?

Comprehensive for a single-param tool with no output schema: it explains the return shape (median, spread, divergence flag, attestation), the preconditions (two live quotes), failure/billing behavior (unlisted ticker not charged), and both free/paid access paths. Nothing an agent needs to call 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% (the single 'symbol' param is fully described with examples), so the schema already does the heavy lifting. The description adds the accepted ticker set (BTC, ETH, SOL, or any ticker), which is mildly helpful context, but no syntax beyond the schema. 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?

States a specific verb and resource (spot crypto price check for a token ticker in USD) and adds concrete scope: cross-checked across five named exchanges, returning a median, spread, and divergence flag. An agent can distinguish this from the verify_* siblings (business, claim, freshness) 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?

Explicit triggers are listed: 'Use it before your agent trades, quotes, values a portfolio or settles on a token price.' The alternatives/paths are also named (free unsigned tier vs. paid signed attestation via payment header or HTTP POST), giving the agent a clear when-and-how decision.

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