Server Quality Checklist

Tool Scores

• dcl_audit_decode_deepB
  3.4/5.0
  Behavior4/5

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

  Annotations already declare readOnly, idempotent, and non-destructive behavior, so the description adds value by disclosing the $0.50 cost, extended output fields, and full chain integrity verification. This gives the agent useful operational context beyond the structured safety hints.

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

  Conciseness4/5

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

  The description is concise, front-loaded with the tool's purpose, and includes cost and key output features in one sentence. It avoids redundancy, though it sacrifices some contextual guidance that could make it more complete.

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

  Completeness3/5

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

  Given the presence of an output schema and complete annotations, the description provides additional useful context like cost and extended verification. However, it lacks a comparison with the dcl_audit_decode sibling and doesn't explain what drift_context is, leaving some contextual gaps for an agent deciding between similar tools.

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

  Parameters3/5

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

  Schema coverage is 100%, with both parameters already described clearly. The description adds no additional parameter-level semantics; it only mentions cost and output characteristics. Since the schema handles the parameter meaning, a baseline of 3 is appropriate.

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

  Purpose4/5

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

  The description clearly identifies this as a deep forensic audit decode for post-action review, with extended output including drift_context and full chain integrity verification. It distinguishes itself from the sibling dcl_audit_decode by the word 'Deep' and the mention of extended output, though it doesn't explicitly contrast the two.

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

  Usage Guidelines2/5

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

  No explicit guidance is provided for when to use this tool versus alternatives like dcl_audit_decode. The phrase 'POST-ACTION' implies a usage context, but there is no clear statement of when to choose this deep variant or any exclusions.

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

• dcl_audit_decodeA
  4/5.0
  Behavior4/5

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

  The description adds helpful behavioral context beyond annotations, including a cost of $0.10 and the tamper-evident nature of the chain. It aligns with the readOnlyHint and idempotentHint annotations, reinforcing that this is a safe, read-only operation. No contradictions with annotations.

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

  Conciseness5/5

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

  The description is a single, front-loaded sentence that conveys the tool's purpose, cost, and key identifier with no unnecessary words. It is highly concise and well-structured.

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

  Completeness4/5

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

  For a simple lookup tool with comprehensive annotations, full schema coverage, and an output schema, the description is adequate. It lacks explicit notes on error handling or payment_id usage, but these are covered by the schema and contextual signals, making the overall package reasonably complete.

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

  Parameters3/5

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

  The input schema already provides complete descriptions for both tx_hash and payment_id, achieving 100% coverage. The description adds no additional parameter detail, so the baseline score of 3 is appropriate.

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

  Purpose5/5

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

  The description states a specific action (retrieves a record) and a specific resource (tamper-evident chain) keyed by tx_hash. The 'Basic' label implicitly distinguishes it from the 'deep' sibling tool, making the purpose unambiguous.

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

  Usage Guidelines3/5

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

  The description does not explicitly state when to use this tool versus dcl_audit_decode_deep. The term 'Basic' implies a simpler audit, but no clear when/when-not guidance or alternative is provided. The schema's payment_id hint gives minor workflow context, but the description itself lacks usage direction.

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

• dcl_evaluate_piiA
  4.2/5.0
  Behavior5/5

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

  Annotations only state readOnlyHint=false, destructiveHint=false, providing no safety profile. The description compensates fully by disclosing the cost ($0.02), method (regex-based, Luhn checksum), and critical behavioral consequence (any finding results in NO_COMMIT). This adds substantial context beyond annotations and no contradiction exists.

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

  Conciseness5/5

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

  Three sentences, each earning its place: states the purpose/cost, explains the scan mechanics and false-positive reduction, and reveals the key outcome (NO_COMMIT). Front-loaded with the tool's function, no wasted language.

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

  Completeness4/5

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

  Given the presence of a true output schema and moderate complexity, the description is largely complete: it covers purpose, cost, mechanism, and outcome. It could be more explicit about the expected workflow (e.g., when exactly to call it relative to other actions), but the 'POST-ACTION' and NO_COMMIT signals convey the essential context.

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

  Parameters3/5

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

  Schema description coverage is 100%, with all three parameters (agent_id, response, payment_id) already described clearly. The description adds no additional parameter-specific meaning beyond what the schema provides, so the baseline of 3 applies.

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

  Purpose5/5

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

  The description states a clear purpose with a specific verb ('Detection Scan') and resource ('PII'), and explicitly names the scope: scanning across 8 personal-data categories. It distinguishes itself from siblings by focusing on PII and mentions a unique method (Luhn checksum) and outcome (NO_COMMIT).

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

  Usage Guidelines3/5

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

  The 'POST-ACTION' prefix implies when to use, and the NO_COMMIT outcome suggests it blocks commits, but there is no explicit statement of when to use versus alternatives or exclusions. No mention of other sibling tools or criteria for choosing this over dcl_evaluate_secrets or dcl_evaluate_safety.

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

• dcl_evaluate_secretsA
  4.2/5.0
  Behavior4/5

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

  The description discloses the regex-based approach, the eight categories, the $0.02 cost, and the critical consequence that any finding produces NO_COMMIT. This goes beyond annotations and provides useful behavioral context.

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

  Conciseness5/5

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

  The description is a single, information-dense sentence. It front-loads the action and cost, and includes a comprehensive list of categories without unnecessary elaboration.

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

  Completeness4/5

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

  With an output schema and complete parameter descriptions, the description covers the tool's purpose, scope, and a key outcome. It is sufficient for this scan tool, though it lacks explicit cross-referencing to sibling tools.

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

  Parameters3/5

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

  Since the schema already provides 100% parameter descriptions, the description does not need to add param details. It does not, but the schema fully covers the semantics, so the baseline score of 3 is appropriate.

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

  Purpose5/5

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

  The description clearly identifies the tool as a secret and credential leak scan, listing eight specific categories it checks. It distinguishes itself from sibling evaluation tools (like dcl_evaluate_pii) by focusing on credentials and adding the NO_COMMIT consequence.

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

  Usage Guidelines4/5

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

  The 'POST-ACTION' label indicates when the tool should be used, and the scan categories imply the type of content to check. However, it does not explicitly name alternatives or state when not to use it, so it misses a full usage guide.

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

• dcl_evaluate_mevA
  4.3/5.0
  Behavior4/5

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

  Annotations are minimal (all false), so the description carries the burden of behavioral disclosure. It adds valuable context: cost ($0.03), decision thresholds (NO_COMMIT for critical or 2+ major findings), confidence nuances (~0.55 vs ~0.05-0.2), and the inclusion of regulatory_reference tags. This goes beyond the annotations and provides meaningful operational detail.

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

  Conciseness5/5

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

  The description is detailed yet tightly packed with actionable information. Every sentence contributes unique value: scope, cost, decision logic, confidence semantics, and regulatory tags. It is front-loaded with the tool name and cost, making it easy to scan.

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

  Completeness5/5

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

  For a compliance-screening tool with nuanced decision logic, the description is remarkably complete. It covers scope, exclusions, cost, severity thresholds, confidence interpretation, and output tags. Since an output schema exists, the absence of explicit return-value descriptions is acceptable. The description fully equips an agent to decide when and how to invoke the tool correctly.

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

  Parameters3/5

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

  Schema description coverage is 100%, so the schema already documents all three parameters. The description does not add significant parameter-level detail beyond what is already in the schema, but it does clarify the purpose of the 'response' parameter (screen for MEV/market-abuse language). This is baseline adequate with high schema coverage.

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

  Purpose5/5

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

  The description uses a specific verb ('screen') and resource ('MEV & Market-Abuse') and clearly distinguishes itself from sibling evaluation tools by focusing on market-abuse language. It also specifies the tool's text-level scope, immediately differentiating it from transaction-level analyzers.

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

  Usage Guidelines4/5

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

  The description provides clear context on when to use the tool (post-action screening of agent responses proposing on-chain/trading actions) and explicitly states what it is not ('not a mempool/transaction analyzer'). However, it does not name alternative sibling tools, so it misses the full 'alternatives' criterion.

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

• dcl_evaluate_output_sanitizerA
  4.5/5.0
  Behavior4/5

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

  Annotations are sparse (readOnlyHint=false, destructiveHint=false). The description adds valuable behavior: cost ($0.02), consistent internal reuse of detection tables, return of sanitized_output with [REDACTED], and the narrow safety-net scope. However, it does not clarify whether the trait readOnlyHint=false implies any side effects or payment behavior beyond the optional payment_id, leaving a small gap.

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

  Conciseness5/5

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

  One dense paragraph, front-loaded with the core purpose, then specific categories, output format, and usage ordering. Every sentence adds unique information with no fluff or redundancy, perfectly sized for the tool's complexity.

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

  Completeness5/5

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

  The description covers purpose, usage sequence, relationship to sibling tools, cost, output structure, and the consistency mechanism with other evaluators. Given the presence of an output schema and annotations, this is fully complete 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.

  Parameters3/5

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

  Schema description coverage is 100% and each parameter (response, agent_id, payment_id) has its own clear description. The tool description does not introduce new parameter-specific meanings beyond emphasizing the 'raw model response' for `response`, which is already captured in the schema. Baseline 3 is appropriate.

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

  Purpose5/5

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

  The description states a specific verb ('strips') and resource ('raw model response'), enumerates exact categories (secrets, PII, crypto material, internal network details, unsafe fragments), and clearly differentiates from siblings by framing itself as the 'FINAL-GATE' and referencing input-side checks and dcl_commit.

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

  Usage Guidelines5/5

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

  Explicitly says when to use: 'Run this as the LAST gate before a response reaches its destination', after input-side checks and immediately before dcl_commit. It also names the alternative tools (dcl_evaluate_jailbreak_crypto, dcl_evaluate_secrets, dcl_evaluate_pii) and provides a substitution rule for NO_COMMIT verdicts.

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

• dcl_evaluate_signalA
  4.5/5.0
  Behavior5/5

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

  With annotations all false, the description carries the full burden and does so admirably. It discloses cost ($0.03), reliance on output text alone (no price feed), the specific heuristic patterns, false-positive potential, non-authoritative status, and the verdict/confidence collapsing rule referencing dcl_evaluate_mev. This goes well beyond annotations.

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

  Conciseness5/5

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

  Though lengthy, every sentence is purposeful: it opens with the tool's name and cost, details the heuristic flags, provides a limitation/caveat, offers an alternative, and explains the verdict rule. It is front-loaded and well-organized, no fluff.

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

  Completeness5/5

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

  The description covers the tool's purpose, behavior, limitations, alternatives, and verdict logic. An output schema exists to handle return structures. It even cross-references a sibling tool for the collapsing rule, providing comprehensive context for an AI agent to correctly select and invoke the tool.

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

  Parameters3/5

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

  The input schema already provides 100% parameter descriptions (agent_id, response, payment_id), so the baseline is 3. The description adds some context about payment ($0.03) and POST-ACTION orientation, but does not significantly enhance parameter-level meaning beyond what the schema already states.

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

  Purpose5/5

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

  The description clearly states a specific verb+resource: 'Market Signal Fabrication Screen' with a precise pattern-based heuristic that flags guaranteed-price-prediction language, absolute-certainty claims, fabricated-price flags, and invented-token flags. It distinguishes itself from sibling evaluators by name and by referencing the local grounding workflow and dcl_evaluate_mev.

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

  Usage Guidelines4/5

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

  The description explicitly states when not to use it ('For a full claim-by-claim check against an actual price-feed snapshot, use the local grounding workflow instead of this live tool') and labels it as a 'heuristic pre-check, not ground truth.' It implies when to use (POST-ACTION, quick screen) but does not enumerate all positive use cases.

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

• dcl_evaluate_walletA
  4.5/5.0
  Behavior5/5

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

  Annotations provide no safety hints, so the description carries the full burden. It discloses that any finding results in NO_COMMIT, that a sanitized_output and masked redacted_sample are returned, and that the real value is never returned or stored server-side. This is highly transparent.

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

  Conciseness5/5

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

  The description is three sentences long, starts with the tool's purpose, and packs essential details (scan targets, outcome, return behavior) without redundancy. The inclusion of the price is a minor but useful addition, and every sentence earns its place.

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

  Completeness5/5

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

  The description is complete for a content-scanning tool: it explains the tool's role, what it detects, the consequence of detection (NO_COMMIT), and the return format. An output schema exists, and the description covers the key return fields, making it sufficiently comprehensive.

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

  Parameters3/5

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

  Schema description coverage is 100% for all three parameters, and the description does not add additional parameter-specific meaning beyond what the schema already provides. The baseline of 3 is appropriate.

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

  Purpose5/5

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

  The description explicitly states the tool scans for BIP-39 seed phrases, private keys, wallet addresses, and API keys near wallet terminology. It also distinguishes itself from other DCL evaluators by noting that wallet secrets have no safe threshold, making the purpose unambiguous.

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

  Usage Guidelines4/5

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

  The description clearly indicates the tool is for post-action evaluation and emphasizes its role as a strict guardrail for wallet secrets. However, it does not explicitly name alternative tools like dcl_evaluate_secrets or state when not to use this tool, so it lacks explicit exclusions.

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

• dcl_pipeline_startA
  4.5/5.0
  Behavior5/5

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

  The description goes far beyond the annotations (which are all false) by disclosing the critical limitation that the returned pipeline_id is not linked to later evaluate_* calls and that there is no server-side session state. It also adds the cost ($0.05) and clarifies it is an identifier/timestamp issuer, not an active tracking session. This is exceptional behavioral transparency.

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

  Conciseness5/5

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

  The description is well-structured: the cost and core purpose are front-loaded, followed by the critical limitation and usage guidance. Every sentence adds value, and the length is appropriate given the need to correct a likely misconception about session linkage.

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

  Completeness5/5

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

  Given the tool's low complexity (simple ID generator) and the presence of an output schema, the description fully covers what the tool does, its limitations, and the intended usage. It is complete enough for an agent to decide when and how to use it without additional information.

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

  Parameters3/5

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

  Schema description coverage is 100%, so the parameters are already fully documented. The description adds no param-specific details beyond what the schema provides, such as how to use scope or ttl_seconds. It does mention 'scope, expiry, initial drift_mode' as part of the returned metadata, but this is output context, not parameter semantics. Baseline 3 is appropriate.

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

  Purpose5/5

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

  The description clearly states the tool generates a new pipeline_id and returns session metadata for grouping related checks. It explicitly distinguishes itself from the sibling evaluate_* tools by framing this as a session/pipeline starter, not an evaluation tool. The verb 'generates' and the resource 'pipeline_id' are specific and unambiguous.

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

  Usage Guidelines4/5

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

  The description gives explicit when-to-use guidance: 'Use this to obtain a shared reference ID for your own client-side grouping of a multi-step audit sequence.' It also provides a clear when-not: 'do not rely on it to automatically aggregate drift across calls.' It does not name alternative tools, but the context makes the appropriate use clear.

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

• dcl_evaluate_fastA
  4.7/5.0
  Behavior5/5

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

  Discloses behavioral details far beyond annotations: $0.01 cost, exact substring phrases, 0.7 confidence threshold, 0.4 confidence penalty, NO_COMMIT/COMMIT verdict logic, and reason field behavior. Annotations provide no safety hints, so the description carries the burden and does so thoroughly.

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

  Conciseness5/5

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

  Three sentences: cost + policy, algorithm mechanics, usage guidance. Dense and front-loaded with the most critical information ($0.01) first. No filler or repetition.

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

  Completeness5/5

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

  With an output schema present, return values need not be explained. The description covers cost, policy details, threshold behavior, verdict logic, and use-case alternatives, making it complete for a simple evaluation tool.

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

  Parameters3/5

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

  Schema coverage is 100%, so baseline 3 applies. The description adds policy context but does not add new parameter-level meaning beyond the schema's existing descriptions for response, agent_id, and payment_id.

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

  Purpose5/5

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

  The description states a specific verb (runs through audit) and resource (server's default policy), with exact forbidden phrases and threshold. It clearly distinguishes from siblings by naming alternatives like dcl_evaluate_strict and dcl_evaluate_jailbreak.

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

  Usage Guidelines5/5

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

  Explicit guidance is given: use as default low-cost first-pass gate before risky actions; switch to strict for broader check or to jailbreak/safety/quality for narrower single-topic checks. This provides when/when-not with named alternatives.

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

• dcl_evaluate_jailbreakA
  4.7/5.0
  Behavior5/5

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

  The description reveals behavioral details beyond annotations: the cost ($0.02), the exact algorithm (substring check, 0.8 confidence threshold, 0.4 confidence penalty per match), and the return format (COMMIT/NO_COMMIT with reason listing matched phrases). This gives substantial context that annotations do not provide.

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

  Conciseness5/5

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

  The description is compact and well-structured, packing cost, algorithm, return behavior, and usage guidance into two sentences with no unnecessary words. It is dense but highly readable.

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

  Completeness5/5

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

  Given the output schema exists, the description does not need to explain return values in detail. It covers all essential aspects: purpose, cost, algorithm, when to use, and how it differs from alternatives. No gaps remain.

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

  Parameters3/5

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

  The input schema already has 100% description coverage for all three parameters, so the baseline is 3. The description does not add parameter-specific semantics beyond what the schema provides; it focuses on the algorithm and use case rather than on the parameters themselves.

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

  Purpose5/5

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

  The description clearly states the tool runs an 'anti_jailbreak' policy with substring checks against 6 forbidden phrases and returns COMMIT or NO_COMMIT. It distinguishes itself from dcl_evaluate_strict, specifying the exact scope (prompt-injection/persona-hijack) and differentiating from sibling tools.

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

  Usage Guidelines5/5

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

  It explicitly provides usage guidance: use this targeted, cheaper check for prompt-injection/persona-hijack risk, and use dcl_evaluate_strict when broader safety/default-policy coverage is needed. This clearly states when to use this tool versus the alternative.

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

• dcl_evaluate_jailbreak_cryptoA
  4.7/5.0
  Behavior5/5

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

  Despite annotations carrying no safety hints, the description discloses substantial behavioral traits: it is pre-action, costs $0.02, returns NO_COMMIT with 'reason' and 'findings' naming matched categories, and screens raw input rather than derived decisions. This goes well beyond what annotations alone convey.

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

  Conciseness5/5

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

  The description is dense but every sentence delivers critical value: purpose, concrete patterns, return behavior, and pipeline ordering. It is front-loaded with the pre-action caveat and cost, and the length is justified by the specificity of the examples.

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

  Completeness5/5

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

  Given the tool's complexity, the description fully covers what it does, when to use it, what it returns, and how it fits into the DCL pipeline. The presence of an output schema reduces the need to specify return structure, but the description already mentions key return fields.

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

  Parameters3/5

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

  Schema description coverage is 100%, with parameter descriptions already covering agent_id, response, and payment_id. The tool description does not add further parameter-level detail, but none is needed because the schema is fully self-documenting.

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

  Purpose5/5

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

  The description uses a specific verb ('screen') and resource ('crypto-specialized instruction-override/jailbreak/injection'), clearly distinguishing it from the sibling 'dcl_evaluate_jailbreak' by emphasizing the crypto-specific angle. It names concrete pattern categories (drain-wallet, unlimited-approval), leaving no ambiguity about the tool's function.

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

  Usage Guidelines5/5

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

  Explicitly instructs to 'run this FIRST in the DCL crypto pipeline, before wallet/trade/MEV checks' and explains why: it screens the input itself rather than a decision built atop it. This provides clear when-to-use guidance and implicitly excludes use after downstream checks have been built.

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

• dcl_evaluate_qualityA
  4.7/5.0
  Behavior5/5

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

  Annotations only indicate non-read-only status and non-destructiveness. The description adds valuable behavior context: cost ($0.03), minimum-confidence threshold (0.85), return behavior (NO_COMMIT with matched phrases), and the 'PRE-ACTION' nature. No contradictions with annotations.

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

  Conciseness5/5

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

  The description is four sentences but each one adds essential information: what it does, how it works, what it returns, and when to use it. It is front-loaded with the tool's name and cost, and contains no redundant or filler text.

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

  Completeness5/5

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

  Given the presence of an output schema and complete parameter schema, the description covers all necessary decision-informing aspects: cost, threshold, policy specifics, output behavior, and usage context. It is fully 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.

  Parameters3/5

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

  Schema descriptions cover all three parameters fully (100% coverage), so the description isn't required to explain them. It adds no parameter-specific semantics beyond what the schema already states, but the baseline of 3 is appropriate for complete schema coverage.

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

  Purpose5/5

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

  The description clearly states the tool's function: it runs the 'content_quality' policy and flags 12 specific types of overconfident or unverifiable phrases. It also explicitly distinguishes itself from jailbreak/safety tools, making its purpose unambiguous relative to siblings.

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

  Usage Guidelines5/5

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

  The description provides explicit when-to-use guidance: 'before publishing agent-written copy or reports' to catch unsubstantiated claims. It also differentiates from alternatives by noting this is 'a different concern from jailbreak or safety phrasing,' effectively covering exclusions.

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

• dcl_evaluate_strictA
  4.7/5.0
  Behavior5/5

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

  The description discloses detailed behavior beyond the neutral annotations: the $0.05 cost, the union of forbidden phrases from three policies, the 0.85 confidence threshold, the 0.4 confidence deduction per matched phrase, and the exact NO_COMMIT condition. It also mentions the `reason` field listing matches, giving full behavioral transparency.

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

  Conciseness5/5

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

  The description is concise and every sentence adds value: cost, policy details, thresholds, verdict logic, and usage guidance. It is front-loaded with the tool's name and cost, and contains no filler or repetition.

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

  Completeness5/5

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

  Given the output schema exists, the description fully covers the tool's behavior, including the verdict conditions and the `reason` field. It provides enough context for an agent to invoke the tool correctly and interpret likely results, without needing to infer missing details.

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

  Parameters3/5

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

  The schema descriptions cover all three parameters (response, agent_id, payment_id) with 100% coverage, so the schema already provides the needed meaning. The description does not add parameter-specific details beyond what the schema states, matching the baseline for high schema coverage.

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

  Purpose5/5

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

  The description clearly states the tool's function: it runs an audit of a response against a broader strict policy, specifying exact thresholds (0.85 vs 0.7) and the verdict outcome. It explicitly differentiates from sibling tool dcl_evaluate_fast, making the purpose unambiguous.

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

  Usage Guidelines5/5

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

  The description explicitly tells when to use this tool instead of dcl_evaluate_fast: when the cost of a false COMMIT is high (e.g., irreversible or high-stakes actions). It provides a clear alternative and a rationale, fulfilling the when/when-not guidance.

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

• dcl_evaluate_tradeA
  4.7/5.0
  Behavior5/5

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

  The description goes far beyond the all-false annotations, disclosing cost ($0.02), the exact decision logic, the requirement for 'risk' as a disclosure marker, the output of an immutable trade_receipt, and its distinction from the top-level audit hash. This is rich behavioral transparency.

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

  Conciseness5/5

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

  The description is information-dense and well-structured. It leads with the tool's purpose, then details the decision rules and output, with no filler. Every sentence contributes distinct value.

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

  Completeness5/5

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

  Given the existence of an output schema and the tool's moderate complexity, the description covers all essential aspects: what is screened, the decision criteria, the receipt output, and the cost. It is complete 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.

  Parameters4/5

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

  Schema coverage is 100%, so the baseline is 3. The description adds extra meaning by explicitly linking the response parameter to trade-decision language and by noting the $0.02 cost, which clarifies when the optional payment_id may be required.

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

  Purpose5/5

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

  The description uses a specific verb ('Screens') and resource ('trade-decision language') and clearly enumerates the unsafe patterns it detects. It distinguishes itself from sibling evaluation tools by focusing on trade decisions and the resulting NO_COMMIT/COMMIT decision.

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

  Usage Guidelines4/5

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

  The description clearly indicates when to use the tool (for screening trade-decision language) and provides detailed behavioral conditions. However, it does not explicitly name alternatives or state when not to use it compared to sibling evaluators, though the trade-specific focus makes the context clear.

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

• dcl_commitA
  4.9/5.0
  Behavior5/5

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

  Beyond annotations, the description discloses that the tool 'always succeeds', is append-only, costs $0.01, and returns a specific receipt format. It also explains the chain-linking behavior, which is not covered by annotations. No contradiction with annotations.

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

  Conciseness5/5

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

  While fairly long, every sentence adds value: purpose, return fields, comparison to evaluate_*, prior_checks explanation, and usage ordering. It is front-loaded with 'FINAL-STEP' and efficiently structured without redundancy.

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

  Completeness5/5

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

  The description covers purpose, return values, parameter semantics, and usage, making it complete for a commit tool. Output schema exists, so it doesn't need to explain returns, but it does anyway, and it addresses the tool's role in the pipeline. No significant gaps.

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

  Parameters4/5

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

  Schema description coverage is 100%, so baseline is 3. The description adds extra meaning to prior_checks by explaining it records downstream pipeline steps with examples, which goes beyond the schema. It doesn't add much for agent_id/decision, but the extra prior_checks detail justifies a 4.

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

  Purpose5/5

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

  The description starts with 'FINAL-STEP' and clearly states the tool 'Writes a trading/agent decision to the append-only Leibniz Layer audit chain' and returns a Merkle-proof-style receipt. It explicitly differentiates from evaluate_* tools by noting it has no pass/fail verdict, distinguishing it from siblings.

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

  Usage Guidelines5/5

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

  Explicitly says 'Always run this LAST, after every other crypto-suite check has passed', providing clear when-to-use guidance. Also contrasts with evaluate_* tools, and recommends passing prior_checks, giving a clear usage pattern.

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

• dcl_evaluate_safetyA
  4.9/5.0
  Behavior5/5

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

  The description discloses many behavioral details beyond the annotations, including the cost ($0.01), the exact policy thresholds, the 0.2 confidence penalty for missing 'AI', the minimum confidence of 0.75, and the NO_COMMIT return behavior with a reason. This far exceeds the bare annotation hints.

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

  Conciseness5/5

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

  The description is dense but every sentence adds value. It front-loads the essential purpose and cost, then details the policy, thresholds, return behavior, and usage guidance without any fluff. Despite being long, it is efficiently structured and easy to parse.

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

  Completeness5/5

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

  Given the tool's complexity, the description fully covers the evaluation criteria, confidence calculation, return values, and usage boundaries. The output schema exists and would explain return format, but the description still clarifies the NO_COMMIT condition and reason, making it complete for an agent to invoke correctly.

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

  Parameters4/5

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

  The input schema already provides 100% description coverage for all parameters, so the baseline is 3. The description adds meaningful context by explaining how the 'response' text is evaluated against the safety policy and how confidence is calculated, enriching the parameter semantics beyond simple field descriptions.

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

  Purpose5/5

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

  The description clearly states the tool's function: runs the 'safety' policy, flags two forbidden disclaimers, requires the substring 'AI', and returns NO_COMMIT when confidence drops below 0.75. It also distinguishes from siblings by explicitly noting it is not a general-purpose safety net and pointing to dcl_evaluate_fast or dcl_evaluate_strict for broader coverage.

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

  Usage Guidelines5/5

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

  The description gives explicit when-to-use guidance: 'Use this when you specifically need to confirm an AI-disclosure marker is present and the two disclaimer phrases are absent.' It also names alternatives for broader coverage, providing clear context and exclusions.

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

• dcl_evaluate_batchA
  5/5.0
  Behavior5/5

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

  With annotations providing no meaningful hints (all false), the description carries the full burden and delivers: pricing ($0.10), independent COMMIT/NO_COMMIT verdicts per item, same logic as single-item tools, results returned in input order, a shared batch_id, and no enforced size limit. This is comprehensive behavioral disclosure.

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

  Conciseness5/5

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

  The description is a single dense paragraph but every sentence earns its place: cost, behavior, item format, policy defaults, return format, and usage recommendation. It is efficiently front-loaded with the pricing and primary action.

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

  Completeness5/5

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

  Given the tool's complexity (batch evaluation, mixed policies, paid action), the description covers all necessary context: how items are structured, which policies are supported, independent verdicts, return format, and cost. It is fully self-sufficient even with the output schema present.

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

  Parameters5/5

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

  Although schema coverage is 100%, the description enriches parameter understanding by detailing the item structure, the default policy value, and listing allowed policy names (default, strict, anti_jailbreak, safety, content_quality). It also clarifies the output shape (results and batch_id), going well beyond the schema's basic descriptions.

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

  Purpose5/5

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

  The description clearly states the tool's function: 'Evaluates a list of items in one call' with a specific verb and resource. It also distinguishes itself from siblings by explicitly positioning it as the batch alternative to multiple single-item evaluate_* calls.

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

  Usage Guidelines5/5

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

  Explicit guidance is provided: 'Use this instead of multiple single-item evaluate_* calls when checking several responses — optionally against different policies — in one priced call.' This clearly states when to use the tool and contrasts it with alternatives.

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