FaultKey · CausalLayer

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

No annotations are provided, so the description carries full burden. It discloses determinism, credit cost, the four-factor engine, incident chaining, jurisdictional threshold variability, and override requirements with rationale. It does not describe rate limits or error states, but the key behavioral traits are 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 moderately long but front-loads the core purpose and verdicts. Every sentence adds value (method, chaining, cost, thresholds, overrides). Minor redundancy ('Uses the same four-factor engine that issues post-hoc certificates... This is a policy gate...') could be trimmed, but overall efficient.

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 (nested objects, jurisdictional variability, overrides, chaining), the description covers purpose, verdicts, engine, chaining, cost, thresholds, and the audit trail requirement. It lacks examples or error handling details, but the core usage and behavioral aspects are sufficiently complete.

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 detailed descriptions for each property. The description adds high-level context (e.g., 'ProposedAction', 'three verdicts') but does not provide additional meaning beyond the schema. Baseline of 3 is appropriate as schema does the heavy lifting.

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

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

The description clearly states it is a deterministic prospective-evaluation gate for passing a ProposedAction before response, yielding one of three verdicts. It distinguishes itself from content safety classifiers and explicitly names the method (FK-METHOD-2026-006). The resource and verb are specific, and the description differentiates from sibling tools like verify_certificate and extract_incident.

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

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

The description explicitly states when to use ('BEFORE the agent delivers a response') and provides context on thresholds per jurisdiction and overrides with audit trail. It clearly distinguishes from content safety classifiers. While it does not list alternative tools for specific scenarios, the usage context is clear and adequate.

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. It discloses Claude-powered extraction, output fields, and cost. But it does not discuss limitations like potential inaccuracies, hallucination risks, or whether it is idempotent. Adequate but could be more transparent about behavioral aspects.

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 plus a note, all front-loaded with key information. No redundant phrases, every sentence adds value.

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 or annotations, the description covers input, output, cost, and relationship to submit_incident. Missing error behavior or rate limits, but overall adequate for a pre-processing tool.

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

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

Schema coverage is 100%, so baseline is 3. Description adds context by explaining that context_hint and jurisdiction_hint improve accuracy, and that output matches submit_incident's schema. Slightly above baseline.

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?

Clearly states it extracts structured incident data from unstructured text, differentiating from siblings like submit_incident. Specifies the output format and purpose as a pre-processing convenience tool.

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?

Explains when to use (before submit_incident) and mentions cost. However, does not explicitly state when not to use (e.g., if data is already structured). Context is clear but lacks exclusion criteria.

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 the description must fully disclose behavior. It indicates the tool is a read operation and free, but omits essential details like authentication requirements, rate limits, or whether the 'index' output is paginated. The behavioral disclosure is incomplete for a tool with no annotations.

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

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

The description is two sentences, tightly written with no extraneous words. It front-loads the primary action and immediately clarifies the two modes. Every sentence is meaningful.

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

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

Given the tool's simplicity (one optional parameter, no output schema), the description conveys the essential behavior. However, it lacks details on the format of the index output and does not explain what the full JSON contains. For a tool with no annotations or output schema, slightly more completeness would be beneficial.

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. The description adds an example value for the optional 'version' parameter ('2026-05-16-v1.6.4-simulation-calibration') and contextualizes it as selecting a specific batch. This adds some meaning beyond the schema, but not enough to raise the score above baseline.

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 returns either an index of all anchor batches or a single batch's full JSON. The specific verb 'Return' and resource 'CausalLayer Tessera anchor batches' provide precise purpose. The sibling tools are unrelated, so no confusion.

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 mentions two modes (index of all batches vs. full JSON for a specific version) and notes it is 'FREE', implying no cost. However, it does not explicitly state when to choose one mode over the other or when not to use the tool. The context is clear but lacks explicit exclusions or 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 provided, the description discloses the output content (fingerprints, algorithms, validity windows, anchor-log repo) and that no authentication is needed. It does not cover error handling or rate limits, but the disclosure is good for a simple query tool.

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

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

The description is two sentences: one for purpose and one for output details and cost. Every sentence earns its place; 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?

Given the tool has only one optional parameter, no output schema, no nested objects, and no annotations, the description fully covers what the tool does, what it returns, and any special conditions (free, no API key). It is complete for its complexity.

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 sole parameter 'issuer_id' is fully described in the input schema with example and behavior. The description adds no new information beyond what the schema already provides, so 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?

The description clearly states the verb 'Return' and the resource 'CausalLayer issuer registry', and distinguishes between returning the full registry or a single record if an issuer_id is provided. This is 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.

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

The description notes that the tool is free and requires no API key, giving clear context for when to use it. However, it does not explicitly state when not to use it or provide alternatives among sibling tools.

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 must fully disclose behavior. It states the tool is pure deterministic and costs 1 credit, implying no side effects. However, it does not discuss authentication requirements, rate limits, or potential errors. The behavioral disclosure is adequate but not exhaustive.

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 one continuous paragraph of five sentences, front-loaded with the main purpose. It covers key points without fluff, though it could be slightly more concise. Every sentence provides useful 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?

Despite having no output schema, the description explains the return values (shares, rules, citations, matrix) and stub handling. It also mentions the discovery endpoint for further context. For a query tool with five parameters and nested objects, this is comprehensive.

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%, but the description adds significant meaning: it explains that flags drive specific jurisdiction overlays (e.g., AI Act/PLD for EU, ACL/CPS 230/VAISS for AU), actors can have coexisting tags, attributable is renormalized, and primaryJurisdiction is used by the EU gate. This adds value 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?

The description clearly states it performs multi-jurisdiction overlay on attributable apportionment, returning shares, rules, citations, and a matrix. It specifies jurisdictions (AU, EU, US, UK, CA) and distinguishes from sibling tools which have different purposes.

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 explicit guidance to use GET /api/v2/jurisdiction/catalog to discover support and stub status, and notes that US/UK/CA are research stubs. It does not explicitly exclude alternatives but provides clear context for when to expect full results.

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; description carries full burden. Discloses cost (1 credit), determinism (byte-identical output), and implicitly that it is a read-only simulator. No contradictions.

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 'Counterfactual remediation simulator'. Every sentence adds value: inputs, outputs, catalog endpoint, cost, determinism. 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?

Given complexity (4 required params with nested objects, no output schema), description fully covers inputs, output semantics, prerequisite catalog, cost, and determinism. Thorough and self-contained.

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% (baseline 3). Description adds value by explaining output structure (isolated vs composite shares) and referencing the FK-METHOD-2026-003 catalog, exceeding schema descriptions.

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 it is a 'Counterfactual remediation simulator', specifies exact inputs (verdict, fourFactorScoring, agents, remediation IDs) and outputs (apportioned shares in isolation and composite). It distinguishes itself from siblings as a unique simulation tool.

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 guidance to fetch remediation IDs via 'GET /api/v2/remediation/catalog'. Implies use when a certificate verdict is available and remediation effects need simulation. Does not explicitly state when not to use or contrast with alternatives, but context is clear.

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 present, so the description carries the full burden. It discloses the return value (signed CausalCertificate, allocations, etc.), cost (50 credits), and three guardrails (PII scan, deterministic-only, minimum evidence). This provides solid behavioral context beyond a simple 'submit'.

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 two concise sentences that front-load the purpose and efficiently list returns, cost, and guardrails. Every sentence adds value without redundancy.

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 (11 parameters, nested objects, no output schema) the description adequately covers high-level returns and constraints but lacks detail on the incident structure and parameter relationships. It is moderately 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.

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

Schema description coverage is only 18%; the description mentions 'three guardrails' corresponding to some parameters but does not explain the majority of parameters like 'title', 'agents', 'events', 'category', 'severity', etc. The description adds minimal meaning beyond the schema for the covered parameters.

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 verb 'submit' and the resource 'AI incident', with a specific purpose of 'deterministic causal liability attribution'. It distinguishes the tool from siblings like 'evaluate_prospective_response' and 'extract_incident' by highlighting the legal and evidentiary focus.

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 outlines the purpose and guardrails but does not explicitly state when to use this tool versus alternatives. There is no mention of prerequisites, use cases, or exclusions, leaving the agent to infer usage context from the purpose alone.

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 fully discloses behavioral traits: cost (50 credits), three guardrails (PII scan, deterministic-only, minimum evidence auto-satisfied), and how trace data is processed (spans become events, service.name grouping, trace_id/span_id propagation). No contradictions.

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 efficient sentences: core function, processing logic, cost and guardrails. No wasted words, front-loaded with the main action.

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

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

Given the tool's complexity (8 params, nested input), the description covers key aspects like transformation logic, cost, and guardrails. It references the sibling submit_incident for output context, but could explicitly describe the response structure since no output schema is provided.

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 only 38%, but the description adds meaning for key parameters (otlp, deterministic_only, pii_acknowledged). However, several parameters (category, currency, jurisdiction, financial_impact_cents) are not described, so the description only partially compensates for low 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 explicitly states it converts an OTLP trace into a FaultKey incident, using specific verbs and resources. It distinguishes itself from the sibling submit_incident by targeting traces instead of incidents.

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 when an OTLP trace is available and mentions that the result is the same as submit_incident, clarifying the relationship. However, it does not explicitly state when not to use this tool or provide alternatives beyond submit_incident.

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 must disclose behavioral traits. It adds cost (1 credit) and production rejection behavior, but does not state whether the tool is read-only, what the return format is, or what happens on failure. Partial disclosure is present.

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 with two sentences, front-loading the purpose and adding cost and environment constraints. It could be slightly more structured, but overall efficiency is good.

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 lack of output schema and annotation, the description fails to explain what the tool returns (e.g., boolean, object with validation details) or how errors are communicated. For a verification tool, this is a significant gap affecting completeness.

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 single parameter with a description ('CausalCertificateV1 object as returned by submit_incident.certificate'), achieving 100% coverage. The tool description adds no further meaning beyond summarizing the verification, so 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?

The description clearly states the verb 'verify' and the resource 'CausalCertificate', specifying the verification aspects (signature, Merkle integrity, issuer status). However, it does not explicitly differentiate from the sibling tool 'verify_certificate_recompute', missing a chance to clarify when to use this one.

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 mentions cost and production behavior, but lacks explicit guidance on when to use this tool vs. alternatives like 'verify_certificate_recompute'. No exclusions or prerequisites are given, so usage context is implied rather than explicit.

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. It explains the recomputation process, lists all checked fields, states the return condition ('PASS only if every checked field matches identically'), and mentions cost. This covers key behavioral aspects well.

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 two sentences: the first states the core action clearly, the second adds key context (strength, cost, and result). Every sentence earns its place with no redundancy.

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 complex nested parameters and no output schema, the description covers all necessary context: what the tool does, how it compares to alternatives, what triggers a PASS, and the cost. It is complete for an agent to understand selection and invocation.

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 is 3. The description adds value by clarifying that 'canonicalInput' is 'the same JSON originally posted to submit_incident or submit_otel_trace', which connects the tool to its sibling workflows.

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 'independently re-derive a CausalCertificate from its canonical input and compare byte-for-byte'. The verb 're-derive' and resource 'CausalCertificate' are specific. It distinguishes from the sibling 'verify_certificate' by noting it is the strongest verification path requiring no trust.

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 with verify_certificate ('same price as verify_certificate') and explains when to use it ('requires no trust in the issuer or signing key'). It implies this is the preferred method for high-assurance verification, but does not explicitly state when not to use it.

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