Skip to main content
Glama

Starwell: World Data & Statistics

Answer a question from verified data

answer

The flagship: ask a natural-language question about the served official statistics. Returns a COMPUTED answer (real Python runs in a sandbox over the verified store, nothing is estimated by a model), the Plotly chart, the Python code, citations to the official tables, and a verification badge per series. CROSS-SOURCE: one question may join series from DIFFERENT agencies, e.g. unemployment from the US BLS, Statistics Canada and the UK ONS in a single call, for correlations, ratios, and like-for-like comparison. How many series one question may join is set by the caller's plan; asking for more returns a series_limit error naming that cap. Returns a refusal when no served series can answer. Takes 10-40 seconds. Requires a free API key (create at /account on the Starwell host; pass Authorization: Bearer dlk_... or set STARWELL_API_KEY on the starwell-mcp bridge). Keyless calls return key_required.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
endNoYYYY-MM-DD
shareNoWhen true, the answer becomes a permanent public page and meta.permalink carries its URL — hand it to the user as a citable link
startNoYYYY-MM-DD
seriesNoOptional: pin exact series, across sources, and skip AI resolution
questionYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / share
      Added value: +{
      +  "description": "When true, the answer becomes a permanent public page and meta.permalink carries its URL — hand it to the user as a citable link",
      +  "type": "boolean"
      +}
  2. Changed1 schema field changed
    • changedInput schema / properties / series / maxItems
      Previous value: -4New value: +6
  3. Changed1 schema field changed
    • changedInput schema / properties / series / description
      Previous value: -"Optional: pin exact series and skip AI resolution"New value: +"Optional: pin exact series, across sources, and skip AI resolution"
  4. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Discloses a lot beyond the single annotation: 10-40 second latency, refusal behavior when no served series match, the series_limit error tied to the caller's plan, and the key_required error with instructions for obtaining and passing a free API key. It also explains that share=true creates a permanent public page, consistent with readOnlyHint=false rather than contradicting it.

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?

Front-loaded with the core purpose and the computed-answer guarantee; each following sentence carries distinct information (cross-source, plan cap, refusal, latency, auth). It is dense and reads as one long run-on block rather than being broken into scannable segments, which costs some readability.

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?

There is no output schema, so the description carries the return-value burden and does so fully (answer, Plotly chart, Python code, citations, per-series verification badge). Combined with auth requirements, latency, and failure modes, an agent has everything needed to invoke it correctly.

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 coverage is high (80%), so the baseline is 3, but the description adds real meaning: it explains that series pins exact series across sources and skips AI resolution, that the joinable-series count is plan-limited, and that share produces a meta.permalink the caller should hand to the user. It does not clarify start/end date semantics beyond the schema's YYYY-MM-DD.

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?

States a precise verb+resource: answer a natural-language question over served official statistics, returning a computed answer, chart, code, citations, and verification badges. It distinguishes itself from read-oriented siblings like get_series or search_catalog by emphasizing cross-source joins and AI resolution, so an agent can tell what unique role this fills.

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?

Gives clear usage context: use it for cross-source joins (e.g. BLS + Statistics Canada + UK ONS in one call), and the optional series param lets callers pin exact series and skip AI resolution. It doesn't explicitly name a sibling alternative or state when NOT to use it, so it stops short of full when/when-not routing.

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.