Skip to main content
Glama

LiveDataLink

by io.github.blackboxfoundry

market_size_estimator

Read-onlyIdempotent

One-call TAM / market-size read for an industry (NAICS) in a US geography. Joins two independent federal sources that both count business activity by NAICS + area so each corroborates the other: US Census County Business Patterns (establishments, employment, annual payroll - needs a Census API key) and BLS QCEW (keyless: private establishment count, total wages, average annual pay, with employment implied from wages / avg pay). Returns the establishment count, employment, and a wage/payroll-based market-size anchor with the per-source evidence. Pass an 'industry' (e.g. 'restaurants', 'software publishers') or an explicit 'naics' code, and an optional 'state' or 'metro' (defaults to national). Market size here is the total annual wages/payroll paid in the industry+area - a concrete lower bound, NOT total revenue/receipts. A source that fails is noted, not fatal. Informational, not a guarantee.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
metroNoOptional 5-digit CBSA/metro code (e.g. '12420' Austin, TX). Census leg only; requires the Census key.
naicsNoExplicit 2 to 6 digit NAICS industry code (e.g. '722' food services, '5112' software publishers). Overrides 'industry'.
stateNoOptional 2-letter state code or 2-digit FIPS (e.g. 'TX', '48'). Omit for a national estimate.
industryNoFree-text industry to map to a NAICS code (e.g. 'restaurants', 'software publishers', 'construction'). Provide this or 'naics'.

TDQS

A4.4/5.0
Behavior5/5

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

Annotations already mark it read-only/idempotent/non-destructive, and the description adds important behavior beyond that: one source requires a Census API key, the other is keyless, source failure is non-fatal but noted, and the returned market-size anchor is a lower-bound payroll estimate rather than revenue. This gives the agent a clear model of side effects, dependencies, and interpretation.

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 information-dense and front-loaded with the tool's one-call purpose. It could be slightly better structured as separate short statements, but every clause contributes essential operational or interpretive detail.

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 no output schema, the description still tells the agent what will be returned (establishments, employment, wage/payroll anchor, per-source evidence), what is required, what happens on partial failure, and how to interpret the result. Nothing essential for invoking or understanding this tool is missing.

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 each parameter is already documented. The description adds useful input context such as industry examples and defaults, but it largely restates the either/or and optional-state behavior already present in the schema, so it does not materially deepen per-parameter meaning.

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 precise verb+resource: a one-call TAM/market-size read for an industry by NAICS in a US geography, and even defines the metric as a wage/payroll lower bound rather than revenue. It differentiates itself from raw data-source siblings by emphasizing that it joins Census CBP and BLS QCEW into a single corroborated estimate.

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?

It clearly sets the context: pass industry or NAICS plus optional state/metro, defaulting to national, and explains that the result is informational rather than a guarantee. It does not explicitly name sibling alternatives or state when not to use it, but the intended use case is unmistakable.

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

All LiveDataLink toolsInspect
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

B3.2/5.0
Disambiguation2/5

Many tools overlap heavily across domains: caselaw_search vs court_case_search vs court_opinion_search, caselaw_citation_lookup vs court_citation_resolver, and a cluster of company due-diligence tools (company_trust_check, counterparty_risk_score, entity_dossier, issuer_diligence_dossier, kyb_aml_evidence_case_file) that all screen a company for sanctions/risk/standing. With 290 tools, an agent will frequently face multiple equally plausible choices for the same user intent.

Naming Consistency3/5

The vast majority of tools follow a clean domain-prefix + snake_case pattern (census_, eia_, fmcsa_, npi_, cfpb_, etc.), but there are notable exceptions: entity_resolve and resolve_entity are reversed duplicates, reg_search (Federal Register) sits next to reg_cfr_search (CFR) with confusingly similar names, and carrier_monitor_recheck deviates from the carrier_vetting_* family.

Tool Count1/5

290 tools is an extreme count under any rubric, far exceeding even the 50+ threshold for the lowest score. While the group-filtering mechanism and meta-tools like list_tool_groups and search_available_datasets mitigate the practical burden, the raw surface is still massively oversized for an agent to select from accurately and efficiently.

Completeness4/5

For a read-only data-aggregation server, coverage is remarkably comprehensive across 59 domains, and generic fallbacks like cdc_dataset_query, eia_series_lookup, fred_observations, and bls_series prevent most dead ends. Minor gaps exist (a single GitHub tool, demo-only property_lookup coverage, no write/update operations anywhere), but the stated data-access purpose is well served.

Resources