US Brand Intelligence

US Brand Signal Confidence Gate

us-brand-signal-confidence-gate

Read-only

Classify buyer-supplied normalized US brand signal scores against explicit accept and review thresholds. Receive sorted accepted, review, and rejected IDs with stable reason codes, counts, and digests; no source or identity claims are made. — $0.05/call, x402 (USDC on base).

Input Schema

TableJSON Schema

Name	Required	Description	Default
`rows`	Yes	One to 100 unique signal IDs with integer normalized scores from 1 to 100. IDs are sorted by the runtime before classification.
`thresholds`	Yes	Accept is inclusive at acceptThreshold; review is inclusive from reviewThreshold up to, but excluding, acceptThreshold. The required ordering marker prevents ambiguity.
`schemaVersion`	Yes	The only supported closed contract version.	1.0

TDQS

A4.2/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=true and destructiveHint=false. The description adds valuable context beyond annotations: 'no source or identity claims are made' clarifies the openWorldHint, and it discloses the output structure (sorted IDs, reason codes, counts, digests) and cost. This is a good behavioral profile for an inline read-only classifier.

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 two sentences plus a pricing note. The first sentence delivers the core purpose, the second covers output and caveats, and the short billing note adds cost transparency. Every sentence earns its place, and the structure is front-loaded.

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 tool's moderate complexity (nested thresholds and rows, no output schema), the description covers the essential aspects: what it does, what it returns, and key caveats (no source/identity claims). It does not detail every reason code or threshold boundary, but the schema fully documents those constraints, so this is sufficiently complete.

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 adds value by tying parameters to behavior: thresholds are used for classification, and rows are buyer-supplied with no identity claims. It does not repeat schema details but reinforces how inputs drive the output, which supports parameter understanding.

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: 'Classify buyer-supplied normalized US brand signal scores against explicit accept and review thresholds.' The verb 'classify' is specific, the resource (normalized US brand signal scores) is clear, and the output (sorted accepted/review/rejected IDs) distinguishes this from sibling tools like rule-router or policy-simulator.

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 implies usage by describing the classification behavior and outputs, but it does not explicitly state when to use this tool versus alternatives like us-brand-signal-rule-router or us-brand-signal-policy-simulator. No exclusions or alternative recommendations are provided, leaving the agent to infer the appropriate context.

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

All US Brand Intelligence tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.8/5.0

Disambiguation2/5

Many tools have overlapping purposes, e.g., us-brand-signal-metrics-aggregator, us-brand-signal-cross-tabulator, and us-brand-signal-brand-summary all produce counts or summaries of the same type of data. The descriptions are detailed, but the boundaries between analyzers, summarizers, and aggregators are unclear enough that an agent may struggle to pick the right one.

Naming Consistency4/5

Most tools follow a consistent 'us-brand-' prefix with descriptive nouns separated by hyphens (e.g., us-brand-signal-batch-splitter, us-brand-evidence-chronology-builder). The exception is 'pricing_info', which uses an underscore and lacks the prefix, creating a minor inconsistency.

Tool Count3/5

At 21 tools, the set is on the heavier side but still manageable for a complex domain like brand intelligence. Many tools are variations on deterministic signal processing, which could be streamlined, but the count itself is not extreme.

Completeness3/5

The tool set covers a broad pipeline for processing buyer-supplied signals and evidence, including splitting, summarizing, routing, and building payloads. However, it lacks any tools for ingesting or fetching data from external sources (except one federal award snapshot), and there is no end-to-end controller that orchestrates the workflow. This leaves notable gaps for a complete 'brand intelligence' lifecycle.

Resources

Need Help?