Cronozen Proof

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

With no annotations provided, the description carries significant weight. It discloses algorithmic complexity (O(n)), processing method (sequential), and specific failure behavior (reports first broken index). Missing explicit read-only/safety declaration and success output format.

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 with zero redundancy. Front-loaded with the core operation (verifies hash chain), followed by implementation details (O(n) sequential) and failure mode. Every word earns its place.

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 no output schema, the description partially compensates by describing the tampering report behavior. However, it omits success output format and doesn't mention potential rate limiting or timeout risks for large O(n) operations on extensive chains.

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%, establishing a baseline of 3. The description references 'domain' and implies index-based verification ('first broken index'), but doesn't explain parameter interactions (e.g., that fromIndex/toIndex enable partial chain verification) or batchSize optimization strategies beyond the schema definitions.

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?

Excellent specificity: states exact action (verifies), resource (SHA-256 hash chain/Decision Proof Units), and scope (entire domain). The mention of 'entire' and 'sequential' effectively distinguishes it from sibling 'proof_verify' which likely handles individual proofs.

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?

Provides implied usage context through 'entire' and O(n) complexity, suggesting this is for comprehensive audits rather than quick checks. However, lacks explicit guidance on when to use vs siblings (particularly 'proof_verify') and doesn't mention prerequisites like domain initialization.

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 disclosure burden. It successfully details the output format standards (JSON-LD v2.0, Cronozen Evidence Ontology) and document contents (6W extraction, hash chain info), but omits operational behaviors such as whether this creates a file, streams data, requires specific permissions, or has side effects.

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 consists of exactly two efficient sentences with zero redundancy. The first sentence front-loads the core action and format, while the second enumerates included components. Every phrase contributes specific domain information (Cronozen, 6W extraction) without 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 simple single-parameter tool without output schema, the description adequately covers the export format, standards compliance, and document contents. The only gap is the lack of explicit return value description (string vs object vs file path), though this is somewhat implied by 'Exports... as JSON-LD'.

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 has 100% description coverage for the single 'id' parameter ('The DPU ID to export as JSON-LD'). The description adds no additional parameter-specific semantics, but given the complete schema documentation, no compensation is necessary, meeting the baseline expectation.

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 ('Exports') with clear resource ('Decision Proof Unit') and output format ('JSON-LD v2.0 proof document conforming to Cronozen Evidence Ontology'). This effectively distinguishes the tool from siblings like proof_verify or proof_get by specifying the standardized export format versus verification or raw retrieval operations.

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 lists specific content included in the export ('compliance status, 6W extraction, hash chain info, and policy snapshot'), which implicitly suggests when to use this tool. However, it lacks explicit guidance contrasting this with alternatives like proof_get or proof_report, and does not specify prerequisites or when-not-to-use conditions.

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?

No annotations are provided, so the description carries full disclosure burden. It effectively describes the data scope (what fields are returned) but omits operational details like authentication requirements, error conditions, idempotency, or rate limits. The term 'Retrieves' clearly signals a read-only operation.

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?

Single sentence structure front-loads the action ('Retrieves...'). The enumerated fields (hash chain position, AI involvement, etc.) earn their place by distinguishing this tool from six siblings. No redundant or wasteful language despite the detailed field list.

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 no output schema existing, the description comprehensively enumerates return data fields (hash chain position, AI involvement, human control, evidence level, compliance). For a single-parameter retrieval tool, this level of output documentation provides sufficient context for agent operation.

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?

Input schema has 100% description coverage for the single 'id' parameter. The description references 'by ID' which aligns with the schema but adds minimal semantic depth beyond what the schema already provides ('The DPU ID to retrieve'). Baseline 3 appropriate 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 uses specific verb 'Retrieves' with resource 'Decision Proof Unit' and scope 'by ID'. It distinguishes from siblings (proof_verify, proof_export_jsonld, etc.) by detailing the specific data fields returned (hash chain position, AI involvement, compliance information) rather than validation status or export formats.

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 implies usage through the detailed field enumeration (use when needing comprehensive DPU metadata), but lacks explicit guidance on when to prefer this over proof_verify (validation) or proof_record (creation). No 'when-not-to-use' or alternative recommendations are provided.

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?

No annotations provided, so description carries full burden. Discloses authentication requirements (none), specific validation logic (SHA-256, chain links), and return type (verification status). Minor gap: does not explicitly confirm read-only/non-destructive nature, though implied by 'verify'.

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 with zero waste. Front-loaded with key differentiator ('Publicly verifies... without authentication'), followed by technical details, then access control summary. Every sentence earns its place.

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 single-parameter tool with 100% schema coverage but no output schema, description adequately covers purpose, verification methodology, and return value hint ('verification status'). Lacks only explicit safety guarantees (read-only confirmation) to be fully complete given zero annotations.

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 DPU ID to publicly verify'), establishing baseline of 3. Description reinforces the DPU concept through context ('DPU's cryptographic integrity'), but does not add format constraints, examples, or syntax details 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?

Description uses specific verb 'verifies' with clear resource 'DPU's cryptographic integrity' and distinguishes from siblings via 'publicly' and 'without authentication' (contrasting with likely authenticated 'proof_verify'). Also specifies technical scope: SHA-256 hash and chain link integrity.

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 states 'without authentication' and 'Anyone can verify — no credentials required,' providing clear context for when to use this over authenticated alternatives. Does not explicitly name sibling alternatives (e.g., 'use proof_verify when authenticated'), but the guidance is clear enough to infer.

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?

No annotations provided, so description carries full burden. It effectively discloses the cryptographic chaining behavior ('SHA-256 hash chain') and return values ('decision_id and chain hash') despite no output schema existing. Could improve by mentioning idempotency, failure modes, or authorization requirements.

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 well-structured sentences with zero waste: purpose (sentence 1), mechanism (sentence 2), return value (sentence 3). Front-loaded with the core action, appropriate length for complexity level.

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 10-parameter write operation with cryptographic behavior and no annotations, the description adequately covers the core mechanism and return structure. Compensates for missing output schema by documenting return values. Could be enhanced with error handling or prerequisite information.

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 baseline applies. The description does not explicitly discuss parameters, but the high schema coverage means all 10 parameters are already well-documented. Description implies the conceptual inputs (AI execution details) without repeating schema specifics.

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?

Description explicitly states the tool 'Records an AI execution as a Decision Proof Unit (DPU)' with specific verb and resource. It clearly distinguishes from sibling verification/export tools (proof_verify, proof_export_jsonld) by specifying this is for creation/recording.

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?

No explicit when-to-use or alternative guidance provided. However, the distinction from siblings is implied through the naming (record vs verify/export/get) and the creation-oriented language. Lacks explicit guidance on when to use versus proof_get or proof_chain_verify.

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?

No annotations provided, so description carries full burden. It successfully discloses return structure (formatted document with decision details, hash chain verification, PDF/JSON-LD links) compensating for missing output schema. However, lacks operational details: no mention of idempotency, side effects, link expiration, or whether this triggers regeneration or retrieves cached reports.

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 tightly constructed sentences with zero redundancy. First sentence front-loads the action and return value; second provides essential sequencing context. Every clause earns its place.

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 no output schema exists, the description adequately explains return values (document structure, formats, verification details). Addresses sibling relationship with proof_record. Minor gap: doesn't mention download link expiration or whether the operation is read-only vs. generating server-side state.

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 the 'id' parameter fully described as 'The DPU ID to generate a report for'. The description mentions 'for a DPU' providing context, but adds no syntax constraints, format examples, or validation rules beyond the schema. Baseline 3 appropriate for complete 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?

Specific verb 'Generates' paired with clear resource 'structured decision report for a DPU'. Implicitly distinguishes from siblings: contrasts with proof_record (which it says to use 'after') and proof_export_jsonld (by mentioning multi-format outputs vs. single export).

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 states temporal sequencing: 'Use this after proof_record'. Provides clear context that this is for creating downloadable evidence reports. Minor gap: doesn't explicitly contrast with proof_export_jsonld for cases when only JSON-LD is needed.

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. It discloses the return value ('verification status') and specific checks performed ('hash consistency'), implying a read-only operation. However, it lacks details on error conditions, rate limits, whether the operation is idempotent, or the format of the verification status.

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 with zero waste. The first sentence establishes the core operation (cryptographic verification), and the second details the specific mechanism (hash consistency) and return value. Information is front-loaded and dense.

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 and no output schema, the description adequately covers the tool's purpose and mentions the return value ('verification status'). However, with zero annotations and no output schema, it lacks completeness regarding error states, authentication requirements, and the structure of the verification status returned.

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%, establishing a baseline of 3. The description adds semantic context by linking 'hash consistency' to the optional 'data' parameter's purpose (re-verification), but does not elaborate on the data format requirements or provide examples beyond what the schema specifies.

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?

Description uses specific verb 'Verifies' with resource 'proof record' and clarifies scope as 'cryptographic integrity' and 'hash consistency'. The phrase 'specific proof record' effectively distinguishes this from sibling 'proof_chain_verify' (chain vs single record) and 'proof_get' (retrieval vs 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?

No guidance provided on when to use this tool versus siblings like 'proof_chain_verify', 'proof_public_verify', or 'proof_record'. No mention of prerequisites (e.g., proof must exist) or when to provide the optional 'data' parameter for re-verification.

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