Primary Source Commodities

Derived Spread

spread.get

Read-onlyIdempotent

Compute a derived spread observation: 3-2-1 crack, soybean crush, WTI-Brent basis, or calendar (calendar requires licensed curve data and may return available=false). Prefer crack/crush/basis for live derived values with formula and inputs.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`root`	No	Optional root symbol for calendar spreads. Example: CL. Ignored for crack/crush/basis.
`type`	Yes	Spread type to compute. Example: crack for 3-2-1 gasoline/distillate crack.

Output Schema

TableJSON Schema

Name	Required	Description
`id`	No	Stable observation id
`name`	No	Human-readable instrument name
`note`	No	Explanation when unavailable or partially degraded
`root`	No	Calendar root when type=calendar
`unit`	No	Unit of measure
`as_of`	No	As-of date for the observation
`value`	No	Observed numeric value
`inputs`	No	Input series ids when derived
`source`	No	Primary source provenance
`derived`	No	True when value is derived
`formula`	No	Derivation formula when derived
`quality`	No	Data quality label
`raw_hash`	No	Hash of raw source payload
`available`	No	False when the spread cannot be computed
`series_id`	No	Underlying series id
`instrument`	No	Instrument code, e.g. CL
`provenance`	No	Retrieval / cache provenance
`license_tag`	No	License / redistribution tag
`observed_at`	No	ISO timestamp when observed
`legs_quality`	No	Per-leg quality when inputs are mixed
`freshness_class`	No	Freshness class for the series

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

First observedJul 26, 2026

TDQS

A4.1/5.0

Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, so the description's addition of 'calendar may return available=false' adds some behavioral context beyond the annotations.

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?

Two sentences front-load the key purpose and limitation, with no redundant or filler text.

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?

The description is complete for a compute tool with two parameters and an output schema, covering types, licensing constraints, and usage preference.

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?

Input schema covers both parameters with full descriptions, so the description does not add parameter-level detail. The tool's overall purpose is clear, but parameter semantics are handled by the schema.

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 uses a specific verb 'compute' and resource 'derived spread observation', lists concrete spread types (crack, crush, basis, calendar), and distinguishes from sibling tools by mentioning calendar's license requirement and recommending alternatives.

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?

The description provides clear context on when to use each spread type: calendar requires licensed data and may return available=false, while recommending crack/crush/basis for live values. It lacks explicit when-not-to-use alternatives but gives actionable guidance.

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

All Primary Source Commodities 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

A4.2/5.0

Disambiguation5/5

Each tool has a distinct purpose: calendar.get for release dates, catalog.list for instrument discovery, price.latest and price.history for prices, inventory.get for inventory, positioning.get for CFTC data, fundamentals.get for reports, fx.latest for FX rates, snapshot.get for sector overview, spread.get for derived spreads, and decision.get for deterministic decisions. No overlapping functionality.

Naming Consistency5/5

All tools follow a consistent noun.verb pattern (e.g., calendar.get, catalog.list, price.latest, snapshot.get). The naming is predictable and makes the tool's purpose clear at a glance.

Tool Count5/5

With 11 tools, the server is well-scoped for a commodity data platform. Each tool covers a distinct aspect (calendar, catalog, prices, inventory, positioning, fundamentals, FX, snapshots, spreads, decisions) without unnecessary bloat.

Completeness4/5

The tool set covers core commodity data needs: price discovery (catalog, latest, history), fundamentals (WASDE, etc.), inventory (EIA), positioning (CFTC), spreads, FX conversion, and summaries. Minor gaps include limited price history (500 points) and no explicit support for options or shipping data, but the overall surface is strong.

Resources

Need Help?