scrapecheck

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 reveals the signature format (canonical sorted-key JSON excluding 'signature') and the in-band delivery of trust evidence, which is non-obvious and valuable context beyond the tool's name.

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 at two sentences, front-loading the tool's purpose and listing returned contents without unnecessary filler. It is well-structured and each sentence contributes meaningful 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 the absence of output schema and annotations, the description sufficiently enumerates all key return elements and explains the signature verification mechanism. This is complete for a no-parameter informational 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?

The tool has zero parameters, so the baseline score is 4. The description adds no parameter-specific details, but none are required.

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 as returning verifier trust information, listing specific items (ed25519 public key, benchmark summary, scope, endpoints). This differentiates it from sibling verification tools that likely perform verification checks rather than provide trust evidence.

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 clear context for when to use the tool: 'the evidence for deciding whether to trust ScrapeCheck's verdicts.' However, it does not explicitly compare with alternative sibling tools or mention when not to use it, so it lacks the full when-to-use/when-not-to-use guidance for 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 fully discloses behavior: it does NOT confirm correctness, uses a signed verdict ('present', 'fail', 'unverifiable'), checks the live page via independent re-fetch, and explicitly states 'no LLM judge'. It also discloses the check_type and pricing. There is no contradiction with annotations (none exist).

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 six sentences, each adding distinct value: key limitation ('not an answer check'), mechanism (re-fetches URL, checks presence), accuracy caveat, return signature, scope, and pricing. It is front-loaded with 'Presence check only', ensuring the most important differentiator appears first. No wasted words.

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?

Despite having no annotations, the description covers all essential contextual aspects: what the tool does, what it does not do, return verdicts, check_type, scope limitations, and cost. Combined with a detailed input schema and an output schema, the agent has complete information 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?

Schema coverage for parameters is 100%, with each parameter having a description. The tool description adds minimal new parameter-level meaning beyond reinforcing that the 'claim' is the value to verify and that verification happens against the live page. This matches the baseline of 3 for high schema coverage.

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 performs a presence check, not an answer check, with the specific verb 'confirms the claimed value appears on the live source page'. It explicitly distinguishes itself from sibling verify_web_field by noting its positive verdict is 'present', never 'pass', and that published accuracy numbers apply only to full 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 contrasts this tool with verify_web_field, stating it is for presence verification only and that accuracy numbers apply to full verification. It also gives a concrete usage boundary ('Scope: server-rendered pages') and mentions the x402 payment mechanism, giving clear context for when to choose this tool over alternatives.

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 full burden and does so thoroughly. It discloses that the tool re-fetches the URL independently, checks for stale cache, uses an independent LLM judge, voids judge votes on restatement mismatch, ensures absence/substitution cannot pass, includes a stable verdict_id and signature, and notes the $0.01 per call cost. This goes far beyond a minimal statement of 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?

The description is long but densely packed with critical information: guarantees, edge cases, cryptographic signing, pricing, and scope. Every sentence serves a purpose and the structure flows from core function to guarantees to verification details to pricing. It borders on verbose but avoids redundancy, so it earns a 4.

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 complexity (cryptographic signing, judge logic, edge cases) and the presence of an output schema, the description covers all essential aspects: success/failure verdicts, guarantee mechanics, scope limitations, security verification path, and cost. The reference to get_verifier_info fills the remaining context for signature verification. Nothing critical 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% with meaningful descriptions for url, asked, and claim. The description reinforces the semantics by explaining how 'claim' is the scraped field(s) and how 'asked' is used by the judge to confirm the answer, which adds value beyond the schema. It doesn't introduce new parameter details but clarifies the verification workflow.

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 verifies a scraped claim against the live source page and returns a signed verdict. The scope and output ('pass', 'fail', 'unverifiable') are explicit, and the 'full' in the title plus the emphasis on an independent judge distinguishes it from the presence-only sibling verify_presence.

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 strong context on when to use the tool (for verified claims with a guarantee) and explicitly notes limitations (server-rendered only, client-rendered returns unverifiable). It does not explicitly name verify_presence as an alternative for simpler checks, but the contrast with presence checking is implied by the detailed judge and live-refetch logic.

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