CausalLayer MCP

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

With no annotations provided, the description fully discloses behavioral traits: deterministic execution, cost (1 credit), per-jurisdiction thresholds, override requirements, and the chain linking to post-hoc certificates. It also clarifies what the tool does not do (content safety classification), providing complete transparency.

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 well-structured and front-loaded with the core purpose. Every sentence adds value, covering verdicts, thresholds, overrides, and chain. It is slightly lengthy but efficient for the tool's complexity, earning a 4 rather than a 5 due to minor redundancy (e.g., 'pure deterministic' is stated twice).

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 (nested object, 2 parameters, no output schema), the description is remarkably complete. It explains the three verdicts, jurisdiction-specific thresholds, override requirements, cost, and deterministic nature. It also contextualizes the tool within the broader incident chain, leaving no critical gaps for an agent to decide usage.

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 the input schema already documents all parameters thoroughly. The description adds context about the tool's overall purpose and the three verdicts but does not provide additional semantics for specific parameters beyond what the schema offers. 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 tool as a 'deterministic prospective-evaluation gate' that evaluates a ProposedAction before delivery, returning one of three verdicts. It distinguishes from siblings by specifying it is a policy gate on structured action metadata, not a content safety classifier. This provides a specific verb-resource combination with clear differentiation.

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 specifies to use the tool 'BEFORE the agent delivers a response', provides context on thresholds per jurisdiction, and explains overrides requiring rationale. However, it does not explicitly list when not to use it or compare directly with sibling tools like verify_certificate or get_anchor_status, leaving some guidance implicit.

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 burden. It discloses that the tool is Claude-powered, costs 10 credits, returns a ready-to-submit object, and mentions the LLM-free scoring engine. It does not detail error handling or privacy, but the core behavioral traits are transparent.

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: first states purpose, second lists inputs and outputs, third adds context and cost. No unnecessary words, efficiently conveys all key information.

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

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

Given 3 well-described parameters and no output schema, the description covers the tool's role, inputs, outputs, cost, and relationship to sibling tools. It lacks information on error cases or extraction failures, but is adequate for a pre-processing convenience 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% with clear parameter descriptions. The tool description adds value by listing output fields (agents, events, severity, jurisdiction, financial impact) but does not elaborate on the parameters beyond what the schema provides. 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 tool's function: extracting structured incident data from unstructured text for submission via submit_incident. It lists input types (news articles, court filings, etc.) and output components (agents, events, severity, jurisdiction, financial impact), and explicitly distinguishes it from the submit_incident sibling 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?

The description positions the tool as a pre-processing step before submit_incident ('required by submit_incident', 'returns a ready-to-submit incident object'). It does not explicitly state when not to use it or list alternatives, but the context is clear given the 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?

It discloses that the tool is free and describes dual output modes, but with no annotations provided, it lacks details on rate limits, error conditions, or authentication 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?

One concise sentence front-loads the main action and includes key details without any 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?

For a tool with one optional parameter and no output schema, the description covers the two possible outputs and their contents; it is mostly complete, though index format is not specified.

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?

While the schema already describes the version parameter, the description adds that omitting it returns an index while providing it returns full JSON, significantly enriching semantics 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 explicitly states the tool returns either the index of all CausalLayer Tessera anchor batches or the full JSON of one batch, clearly distinguishing it from sibling tools which have very 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 implies usage for retrieving anchor batch status but does not provide explicit when-to-use or when-not-to-use guidance nor mention alternative tools for similar tasks.

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 behavioral disclosure burden. It indicates the tool is a read operation (returns registry records) and is free. It does not mention restrictions, rate limits, or data freshness, but the disclosed behavior is clear and non-contradictory.

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: first states primary action, second elaborates on contents and cost. Efficient and front-loaded. No superfluous text.

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?

The tool is simple (one optional param, no output schema). The description adequately covers what it returns and that it requires no API key. It does not detail return format, but given the simplicity and lack of output schema, this is not a major gap.

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 a single optional parameter. The description adds an example value ('causallayer-prod-2026-q2') and states the behavior when omitted, which adds marginal value beyond the schema description. 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 it returns the CausalLayer issuer registry or one issuer record, and lists the contents (fingerprints, algorithms, validity windows, anchor-log repo). This is specific and aligns with the tool name. It does not explicitly differentiate from sibling tools, but the unique name and context make 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.

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

The description mentions 'FREE — no API key required', which is a useful usage note. However, it provides no guidance on when to use this tool versus alternatives like verify_certificate or query_jurisdiction_overlay. Usage context is implied but not 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 fully discloses key behaviors: it is deterministic, costs 1 credit, renormalizes the apportionment sum, and indicates stub status for US/UK/CA. It also mentions the output structure (shares, rules, citations, matrix).

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 information-dense but front-loaded with the core purpose. It covers inputs, outputs, limitations, and usage hints in a single paragraph without redundancy. Could be slightly more structured, but 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 of 5 parameters (3 required), nested objects, and no output schema, the description adequately explains the tool's purpose, inputs, outputs, behavioral traits (deterministic, credit cost, stub status), and how to check support. It leaves little ambiguity for an agent.

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. The description adds value by explaining the overall input semantics (e.g., 'union of jurisdiction role tags', 'union of flags') and describing the output, which is not in the schema. It also hints at flag semantics with examples.

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 the function: given an apportionment, actor tags, and flags, it returns post-overlay shares for up to five jurisdictions with triggered rules, citations, and a matrix. It distinguishes itself from sibling tools by its specific jurisdiction overlay purpose.

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 advises using GET /api/v2/jurisdiction/catalog to discover support and stub status, and notes that only AU and EU are fully implemented while others are stubs. This provides context on when to use the tool but does not explicitly exclude alternatives.

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

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

With no annotations, the description carries full burden. It discloses determinism (byte-identical results), cost (1 credit), and implicitly indicates it is a read-only operation via the GET method mention. It does not discuss authentication or rate limits, but the provided details are substantial for safe invocation.

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 and front-loaded. The first sentence summarizes the tool's purpose and inputs. Every sentence adds value: inputs, outputs, reference to catalog, cost, and determinism. There is no redundant or unnecessary text.

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 (4 parameters with nested objects, no output schema), the description is fairly complete. It covers what inputs are needed, what outputs are returned, and provides additional context like cost, determinism, and catalog reference. The lack of output schema is compensated by describing the output in words.

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 schema already defines parameters. The description adds context by stating that parameters come from a CausalCertificate, that remediations are from the FK-METHOD-2026-003 catalog, and that each remediation can optionally pin an appliedToParty. This adds meaning beyond the raw 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?

The description clearly identifies the tool as a counterfactual remediation simulator, specifying the inputs (verdict, fourFactorScoring, agents, remediation IDs) and outputs (apportioned shares, composite shares). It references the catalog endpoint for obtaining remediation IDs, distinguishing it from sibling tools like verify_certificate.

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 the tool: given a certificate's verdict, fourFactorScoring, agents, and remediation IDs. It mentions the cost and deterministic behavior, and references the catalog endpoint for obtaining valid IDs. It does not explicitly exclude scenarios, but the context is clear enough for appropriate usage.

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 the full burden. It mentions the returns, cost, and guardrails, but does not disclose side effects, idempotency, rate limits, or error conditions. It adds value but lacks 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.

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

The description is three sentences, front-loaded with purpose and returns, followed by cost and guardrails. Every sentence earns its place with no 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?

Given the tool complexity (11 parameters, no output schema, no annotations), the description covers purpose, returns, and guardrails but lacks guidance on usage flow, failure modes, and relationship to siblings. It provides a basic context but is not fully 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 only 18%, so the description must compensate. It adds meaning to pii_acknowledged (PII scan) and deterministic_only (must be true), but fails to clarify many other parameters like category, severity, jurisdiction, events, agents, and financial_impact_cents.

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'), resource ('AI incident'), and purpose ('deterministic causal liability attribution'). It lists expected returns, including CausalCertificate and liability allocation, which distinguishes it from siblings like extract_incident or simulate_remediation.

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 specifies cost (50 credits) and three guardrails (PII scan, deterministic-only, minimum evidence), giving clear conditions for use. However, it does not explicitly say when not to use this tool versus 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, description fully discloses cost (50 credits), three guardrails (PII scan, deterministic-only, minimum evidence), and behavioral details (spans to 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?

Compact 4-sentence description, front-loaded with main action. Every sentence adds unique value: conversion, mapping, cost, guardrails. 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?

Covers main behavior, guardrails, and parameter mapping. Lacks explanation of optional parameters and explicit output details, but mentions returning same CausalCertificate as sibling. Adequate for the 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?

Schema coverage is low (38%). Description adds meaning for otlp (OTLP JSON payload with resourceSpans), pii_acknowledged (G1), deterministic_only (G2). However, category, currency, jurisdiction, financial_impact_cents remain unexplained.

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 'Convert' with resource 'OpenTelemetry OTLP JSON trace' and target 'FaultKey incident'. Clearly distinguishes from sibling submit_incident by input format and mentions deterministic CausalCertificate.

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?

States when to use: for converting OTLP traces. Implicitly contrasts with submit_incident. Does not explicitly list when not to use, 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?

Discloses cost (1 credit) and environment-specific behavior (rejection of non-active issuers in production). With no annotations, the description provides useful behavioral context beyond the schema, though it doesn't state whether the operation is read-only or modifies state.

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, front-loaded with purpose, followed by cost and environment detail. No unnecessary words; 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?

Lacks description of return value or output structure. With no output schema, the agent needs to know what the tool returns (e.g., boolean, status object). The description omits this, reducing completeness for a verification 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%, but the description adds provenance ('as returned by submit_incident.certificate'), which clarifies the expected source of the certificate object and aids correct usage.

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 the verb 'verify' and the resource 'CausalCertificate,' listing the verification aspects (signature, Merkle integrity, issuer status). The mention of 'end-to-end' distinguishes it from the sibling verify_certificate_recompute.

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?

Implies use for comprehensive verification, cost of 1 credit, and production rejection of non-active issuers. However, no explicit guidance on when to use this tool vs the sibling verify_certificate_recompute, or 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.

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

With no annotations, the description must cover behavioral aspects. It explains the recomputation and comparison process, lists all checked fields, and mentions cost. However, it does not describe what happens on mismatch (return value structure) or 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 is concise: two sentences plus a list of fields. Every sentence adds value, and the structure is clear. No fluff or repetition.

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, no output schema), the description covers the tool's purpose, parameters, and verification approach adequately. Missing return format details, but the core behavior is well explained.

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?

Both parameters have schema descriptions (100% coverage). The description adds practical context for canonicalInput by noting it's the original incident JSON from submit_incident or submit_otel_trace, which aids agent understanding 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 the tool's function: independently re-derive a CausalCertificate and compare byte-for-byte. It specifies the verification path, lists checked fields, and distinguishes it from verify_certificate by emphasizing no trust in issuer.

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 context about when to use (strongest verification, no trust needed) but lacks explicit guidance on when not to use or how it compares to alternatives beyond cost. It implies a use case but does not fully address decision criteria.

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