Skip to main content
Glama

AINumbers Fintech Intelligence Suite

SB 53 Frontier Scope Checker

check_sb53_frontier_scope
Read-onlyIdempotent

SB 53 Frontier Scope Checker: OpenChainGraph compute node (compliance_mandate). Deterministic OpenChainGraph compute node. By default (compute:"auto") inputs are computed server-side on Cloudflare Workers for gpu:false nodes with a registered kernel; compute:"browser" forces client-side execution and returns a browser delegation URL instead. gpu:true nodes always delegate to the browser. Inputs are processed transiently to compute the response and are not stored, logged, or retained. Use synthetic or anonymised inputs only. Exports an AP2 artifact with execution_hash for chain provenance. Open at: https://ainumbers.co/chaingraph/art-316-sb53-frontier-scope-checker.html FV-status (published/proven/still-trusted for this spec): /fv-status/565f2dd45a55e0ff0f8dafde8c1080f9e1484b32a5aaa96f4d7739a236b9258a.json — a snapshot, not a subscription; this receipt verifies offline regardless of whether that file is ever fetched. Summary: Routes supplied model compute (FLOPs, as a decimal string above the 2^53 safe-integer range) and developer annual revenue through the California SB 53 Transparency in Frontier Artificial Intelligence Act (eff. Outputs: compute_flops, flop_threshold, is_frontier_model, is_large_frontier_developer, large_developer_revenue_threshold_usd, obligation_set, statute_citation. Output schema: call describe_tool("check_sb53_frontier_scope").

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "check_sb53_frontier_scope"
  }
}

Input Schema

NameRequiredDescriptionDefault
computeNoCompute mode (v0.4 Compute Binding). "auto" (default) = server for gpu:false nodes with registered kernels; "server" = force server-side; "browser" = always return browser delegation URL. gpu:true nodes always delegate.
parent_hashesNoexecution_hash values from upstream ChainGraph AP2 artifacts to chain from (sets chain.parent_hashes in the export).
parent_tool_idsNotool_id values matching parent_hashes, in the same order.
policy_parametersNoInput parameters for this tool's decision function. For gpu:false nodes with a registered kernel, these are computed server-side when compute is "auto" or "server". Required: annual_revenue_usd, compute_flops. Unknown keys are refused.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / $schema
      Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"
  2. Changed3 schema fields changed
    • changedInput schema / properties / policy_parameters / description
      Previous value: -"Input parameters for this tool's decision function. For gpu:false nodes with a registered kernel, these are computed server-side when compute is \"auto\" or \"server\". See the tool's manifest for field names."New value: +"Input parameters for this tool's decision function. For gpu:false nodes with a registered kernel, these are computed server-side when compute is \"auto\" or \"server\". Required: annual_revenue_usd, compute_flops. Unknown keys are refused."
    • addedInput schema / properties / policy_parameters / properties
      Added value: +{
      +  "annual_revenue_usd": {},
      +  "compute_flops": {}
      +}
    • removedInput schema / properties / policy_parameters / propertyNames
      Removed value: -{
      -  "type": "string"
      -}
  3. Changed1 schema field changed
    • changedOutput schema / (root)
      Previous value: -{
      -  "properties": {
      -    "compute_flops": {
      -      "type": "string"
      -    },
      -    "flop_threshold": {
      -      "type": "string"
      -    },
      -    "is_frontier_model": {
      -      "type": "boolean"
      -    },
      -    "is_large_frontier_developer": {
      -      "type": "boolean"
      -    },
      -    "large_developer_revenue_threshold_usd": {
      -      "type": "integer"
      -    },
      -    "obligation_set": {
      -      "type": "array"
      -    },
      -    "statute_citation": {
      -      "type": "string"
      -    }
      -  },
      -  "type": "object"
      -}New value: +null
  4. Changed1 schema field changed
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
      +  "properties": {
      +    "compute_flops": {
      +      "type": "string"
      +    },
      +    "flop_threshold": {
      +      "type": "string"
      +    },
      +    "is_frontier_model": {
      +      "type": "boolean"
      +    },
      +    "is_large_frontier_developer": {
      +      "type": "boolean"
      +    },
      +    "large_developer_revenue_threshold_usd": {
      +      "type": "integer"
      +    },
      +    "obligation_set": {
      +      "type": "array"
      +    },
      +    "statute_citation": {
      +      "type": "string"
      +    }
      +  },
      +  "type": "object"
      +}
  5. Added

TDQS

B3.2/5.0
Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description does add real behavior beyond that: inputs are processed transiently with no storage or logging, compute:"browser" returns a delegation URL rather than a result, gpu:true nodes always delegate, and an AP2 artifact with execution_hash is exported for provenance. Those are useful, but the compute-mode text largely restates the schema's own enum description.

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

Conciseness2/5

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

The definition is badly front-loaded: it opens with a repeated 'OpenChainGraph compute node' framing and a full FV-status URL with a 64-character hash before reaching what the tool actually computes. The SB 53 sentence is also literally truncated mid-clause ('Act (eff. Outputs: ...'), and 'Output schema: call describe_tool(...)' is a pointer that substitutes for information rather than providing it.

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 nested-object, chained-artifact tool with no output schema, the description is reasonably complete: it lists every returned field and names the statute being applied. What is missing is the actual statutory thresholds (the sentence that would state the FLOP and revenue cut-offs is cut off before giving them), which an agent would otherwise have to infer from output field names.

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 the baseline is 3; the description earns above baseline by specifying that compute_flops must be supplied as a decimal string above the 2^53 safe-integer range, which the schema's untyped {} fields never say. It also calls out that annual_revenue_usd and compute_flops are required and that unknown keys are refused, reinforcing the nested policy_parameters object.

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 'Summary:' sentence names a specific verb and resource — routing model compute FLOPs and developer annual revenue through the California SB 53 frontier-model thresholds — and enumerates the resulting decisions (is_frontier_model, is_large_frontier_developer). It is genuinely specific, but the actionable statement is buried after two sentences of infrastructure boilerplate, and it never names a sibling (e.g. assess_traiga_exposure, run_ai_act_highrisk_fit) to contrast against.

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?

There is no when-to-use or when-not-to-use guidance and no routing to alternatives among the many adjacent AI-governance scope checkers in the sibling list. The only directive present is an input-handling constraint ('Use synthetic or anonymised inputs only'), which is not selection guidance.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.