US natural gas for agents: LNG feedgas, outages, EIA storage, Henry Hub curve, COT, charts
Glama MCP Gateway
Connect through Glama MCP Gateway for full control over tool access and complete visibility into every call.
Full call logging
Every tool call is logged with complete inputs and outputs, so you can debug issues and audit what your agents are doing.
Tool access control
Enable or disable individual tools per connector, so you decide what your agents can and cannot do.
Managed credentials
Glama handles OAuth flows, token storage, and automatic rotation, so credentials never expire on your clients.
Usage analytics
See which tools your agents call, how often, and when, so you can understand usage patterns and catch anomalies.
Average 4.4/5 across 3 of 3 tools scored. Lowest: 3.9/5.
Each tool addresses a distinct aspect of natural gas data: fundamental score, production nowcast, and storage nowcast. There is no functional overlap, and agents can easily differentiate them.
All tools follow a consistent 'get_us_natural_gas_<specific_measure>' pattern, using snake_case and clear descriptive names. The naming is uniform and predictable.
Three tools cover key indicators for natural gas monitoring. While the set is concise, it avoids bloat and each tool adds significant value. A slight increase might be justified, but the current count is appropriate for the focused scope.
The tools provide core supply and demand indicators (production, storage, and a composite score incorporating demand). Minor gaps like a separate demand tool exist, but the composite score partially addresses them, making the surface fairly complete for monitoring purposes.
get_henry_hub_cot_positioningASpeculative positioning in Henry Hub natural gas from the weekly CFTC
Commitments of Traders report (futures and options combined): managed
money net position, its weekly change, its percentile against three years
of history, producer net, open interest and its change, plus a
plain-English read. Reports lag the market — days_stale says by how
much. Full data on both scopes.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
| Name | Required | Description |
|---|---|---|
| asof | No | |
| data | No | |
| note | No | |
| tool | No | |
| scope | No | |
| stale | No | |
| disclaimer | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already mark the tool as read-only and idempotent. The description adds behavioral context: it notes the data lags the market and that `days_stale` indicates the lag. No contradictions with annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences, front-loaded with the core purpose and detailed fields. Every sentence adds value: the first covers scope and data, the second notes lag and staleness. No redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With an output schema present, the description does not need to explain return format. It fully describes the data content, staleness, and scope. The mention of 'both scopes' is ambiguous but does not detract from completeness.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
There are zero parameters, and schema coverage is 100%. The description does not need to add parameter info. Baseline for no parameters is 4.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly specifies the resource (Henry Hub natural gas speculative positioning from CFTC CoT report) and enumerates the exact data fields (managed money net, weekly change, percentile, producer net, open interest, change, plain-English read). It is distinct from sibling tools that cover forward curves, LNG, storage, etc.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage context (weekly CFTC report on speculative positioning) but does not explicitly state when to use or not use, nor mention alternatives among siblings. However, the context is clear enough for an agent to infer appropriate use.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
get_henry_hub_forward_curveAHenry Hub natural gas futures forward curve by delivery month: price, session move, volume, and the same months a week, a month and a year ago for year-over-year context. Pro scope adds today's live prices and the curve-shape read — how much of the front-end move reached the far end and how unusual that pass-through is against two years of comparable days (a front-only move is a near-term balance story, a parallel shift is not). Market context, not investment advice.
| Name | Required | Description | Default |
|---|---|---|---|
| months | No | How many delivery months of the curve to return, starting from the front month. |
| Name | Required | Description |
|---|---|---|
| asof | No | |
| data | No | |
| note | No | |
| tool | No | |
| scope | No | |
| stale | No | |
| disclaimer | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false. The description adds valuable context: it returns historical comparisons, 'Pro scope adds today's live prices and curve-shape read', and includes a disclaimer ('Market context, not investment advice'). No contradictions.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Description is dense but efficient; it front-loads the main output and then adds details about Pro scope. Could be slightly more concise, but no extraneous sentences.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Output schema exists, annotations are rich. The description covers key aspects: what data is returned, historical context, and Pro scope features. It provides a complete picture for an agent to decide to use this tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Only one parameter (months) with schema coverage 100% (description already states 'How many delivery months...'). The tool description does not add additional parameter semantics beyond the schema, so baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Clearly states the tool returns 'Henry Hub natural gas futures forward curve by delivery month' with price, session move, volume, and historical comparisons. The description differentiates from siblings by specifying the unique data (forward curve) vs. other tools (e.g., COT, storage, weather).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Does not explicitly state when to use or not use this tool, but the sibling tools are all distinct (e.g., weather, storage, production), so context makes it clear. A brief usage hint would improve it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
get_us_lng_feedgasADaily LNG feedgas for US liquefaction terminals (Bcf/d) — the export
pull on the domestic natural gas balance, nowcast from pipeline
nominations on the terminals' electronic bulletin boards (split across
operators, no single public source). Returns today's total with a regime
label (loose / below_normal / normal / tight) measured against nameplate
capacity and the 30-day mean, utilization, and the daily history.
Pro scope adds the per-terminal breakdown, the measured-vs-estimated
split and movers — who drove the change versus yesterday. Demo scope
returns the same fields, breakdown included, as of a week ago.
| Name | Required | Description | Default |
|---|---|---|---|
| history_days | No | How many days of daily feedgas history to return (1-400). |
| Name | Required | Description |
|---|---|---|
| asof | No | |
| data | No | |
| note | No | |
| tool | No | |
| scope | No | |
| stale | No | |
| disclaimer | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond the readOnly, idempotent, and destructive hints in annotations, the description adds critical behavioral details: nowcast from pipeline nominations, lack of single public source, regime label calculation, and Pro vs Demo scope differences, with no contradictions.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is front-loaded with the core purpose and output, but is somewhat verbose, including scope details that could be separated. Nonetheless, it is well-structured and each sentence adds value.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the presence of an output schema, the description does not need to detail return fields. It adequately covers purpose, key outputs (regime, utilization, history), and scope differences, though slightly more detail on the regime thresholds could help.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 100% coverage with a description for the single parameter history_days, so the baseline is 3. The description does not add further semantic meaning beyond what the schema already provides.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the resource (US LNG feedgas), metric (Bcf/d), and context (export pull on domestic natural gas balance), distinguishing it from sibling tools focused on prices, storage, or outages.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for obtaining daily feedgas data with regime labels and scope differences, but does not explicitly state when to use this tool over alternatives like get_us_lng_plant_outages.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
get_us_lng_plant_outagesAOperating status of every US LNG export plant (Sabine Pass, Corpus Christi, Freeport, Plaquemines, Calcasieu Pass, Cameron, Cove Point, Golden Pass, Elba Island): online / partial / down / ramping, current flow versus nameplate, capacity offline in Bcf/d and total ramping capacity. Status is inferred automatically — pipeline measurement first, news second — and each record says which source decided it. Pro scope adds the news headline behind the status and the start/end dates it claims. Demo scope lags 7 days.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
| Name | Required | Description |
|---|---|---|
| asof | No | |
| data | No | |
| note | No | |
| tool | No | |
| scope | No | |
| stale | No | |
| disclaimer | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Description goes beyond annotations (readOnlyHint, etc.) by explaining that status is 'inferred automatically — pipeline measurement first, news second' and 'each record says which source decided it'. Also states Demo scope lags 7 days. No contradiction with annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Description is front-loaded with key information (plants, statuses) and well-structured. Slightly verbose with the scope explanation, but every sentence adds value. Could be trimmed slightly without losing meaning.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With zero parameters and an output schema present, the description completely covers what the tool returns: plant list, status types, flow vs nameplate, capacity offline/ramping, source attribution, and data freshness. No gaps.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has no parameters (0 properties). The description fully compensates by explaining what data the tool returns in detail, so agents understand the output without needing parameter guidance.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description explicitly states the tool returns 'operating status of every US LNG export plant', lists all plant names, status types, and metrics (flow, capacity). This clearly distinguishes it from sibling tools like get_us_lng_feedgas or get_henry_hub_forward_curve.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit when-to-use vs alternatives, but the tool is unique among siblings (no other outage tool exists). The description mentions scope differences (Pro vs Demo lags 7 days) which provides partial usage context. Lacks explicit exclusions or alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
get_us_natural_gas_chartAA ready-made chart of US natural gas fundamentals as a PNG image, the
same card we publish to our own channel: LNG feedgas, the fundamental
score with its signal contributions, GFS/ECMWF weather runs, EIA storage
against the 5-year normal, a Gantt of liquefaction outages, the Henry Hub
forward curve, or CFTC managed-money positioning. Use it when a human is
going to look at the answer — the numbers behind every card are available
as data from the other tools. kind is one of lng_feedgas,
fundamental_score, weather_models, storage, lng_outages, forward_curve,
cot_positioning. Requires a token: charts are the one thing demo scope
cannot serve delayed.
| Name | Required | Description | Default |
|---|---|---|---|
| kind | No | Which card to render: lng_feedgas, fundamental_score, weather_models, storage, lng_outages, forward_curve or cot_positioning. | lng_feedgas |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint and destructiveHint. The description adds authentication requirement (token) and scope limitation (demo cannot serve delayed). No contradictions.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences plus a clear line about kind and token. Every sentence adds essential information without redundancy. Front-loaded with core functionality.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema, but description thoroughly lists all chart types and their content. For a chart tool, it provides sufficient context about what the PNG will contain.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, baseline 3. The description adds value by explaining all kind options and their context, plus token requirement, beyond the schema's description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description explicitly states it produces a PNG image chart of US natural gas fundamentals, listing specific cards. It clearly distinguishes from sibling data tools by noting that the chart is for human viewing.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Provides direct guidance: 'Use it when a human is going to look at the answer', and contrasts with data tools that provide numbers. This helps the agent choose appropriately.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
get_us_natural_gas_fundamental_scoreAComposite fundamental pressure score for US natural gas / Henry Hub (-100..+100), built from 5 z-normalized signals (EIA storage vs 5-yr norm, 4-week surplus change, power burn, 7-day cooling and heating demand), with per-signal breakdown, its percentile against its own history and the latest NOAA degree-day forecast revision. ALWAYS returns the score's measured out-of-sample accuracy (walk-forward, against a baseline) and a disclaimer: this is market analysis, NOT investment advice. Set include_history=true for the daily score series with Henry Hub spot prices (~1000 points, off by default). Demo scope returns a 14-day-delayed score without the signal breakdown.
| Name | Required | Description | Default |
|---|---|---|---|
| include_history | No | Add the daily score series with Henry Hub spot prices (~1000 points); off by default because it is long. |
| Name | Required | Description |
|---|---|---|
| asof | No | |
| data | No | |
| note | No | |
| tool | No | |
| scope | No | |
| stale | No | |
| disclaimer | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description adds significant behavioral context beyond annotations: it always returns out-of-sample accuracy and a disclaimer, include_history defaults off due to length, and demo scope returns a 14-day-delayed score without signal breakdown. This clearly communicates what the tool does and its limitations, complementing the read-only, idempotent annotations without contradiction.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is dense but well-organized, moving from the core score definition to signal breakdown, guaranteed outputs, and parameter options. Each sentence adds value, though it is on the longer side; it could be slightly tightened without losing critical information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description fully covers what the score measures, how it is constructed, what outputs to expect (including accuracy and disclaimer), optional history behavior, and demo limitations. With an output schema present, this is comprehensive for a complex analytic tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Although the schema already describes include_history, the description enriches it by explaining the rationale for the default (off because it is long) and specifying that it returns the daily score series with Henry Hub spot prices. This goes beyond the raw schema and helps the agent decide whether to set it.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly defines a composite fundamental pressure score for US natural gas/Henry Hub, specifying the range (-100..+100), the five input signals, and the output components (breakdown, percentile, forecast revision). This distinguishes it from sibling tools that focus on charts, news, storage, or production, making its purpose unambiguous.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage context: it is the go-to tool for a fundamental pressure score, with optional history and a demo mode. However, it does not explicitly state when to use this tool versus alternatives like get_us_natural_gas_pressure_summary or weather models, nor does it provide exclusionary guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
get_us_natural_gas_market_briefASTART HERE for any US natural gas / Henry Hub question: the whole dashboard in one call, so an agent does not have to chain five tools and stitch the numbers itself.
Returns, as of the latest data we hold: (1) pressure — every fundamental
we track (LNG feedgas, liquefaction outages, weather-model shifts, the
EIA injection pace, power burn vs normal, NOAA cooling demand, total
demand week-over-week) with its direction on price, strength, the number
behind it and a plain-English sentence, plus an overall roll-up naming
which signals push down and which push up; (2) demand — total US demand
in Bcf/d with its components (power burn, LNG feedgas, industrial,
residential+commercial, Mexican exports, other), the change against the
same weekday a week ago, per-component week-over-week deltas, power burn
year-over-year, and supply minus demand; (3) storage, production, the
Henry Hub forward curve six months out and CFTC managed-money
positioning, each reduced to its latest reading.
Also returns `note` — the rules for reading these numbers correctly:
demand has a weekly profile so day-to-day moves are noise and only
week-over-week comparisons mean anything, the monthly EIA components are
flat steps rather than live signals, and the curve and positioning are
context, not a forecast. Long histories and daily series are deliberately
left out; fetch the dedicated tool when you need one.
Direction is the sign of a deviation from normal, not a probability that
price moves. Market analysis, NOT investment advice. Demo scope returns
the same shape on delayed data.| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
| Name | Required | Description |
|---|---|---|
| asof | No | |
| data | No | |
| note | No | |
| tool | No | |
| scope | No | |
| stale | No | |
| disclaimer | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already mark this as a safe, idempotent, read-only operation, and the description adds substantial behavioral context: the 'note' clarifies week-over-week vs day-to-day interpretation, flat monthly steps, context-not-forecast framing, direction-as-deviation-not-probability, and demo scope returning delayed data on the same shape. This goes well beyond the annotations without contradicting them.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is long but well-structured and front-loaded with the key purpose. Each section—purpose, return contents, interpretation rules, exclusions—earns its place, and the numbered return list makes scanning easy. Slightly more verbose than strictly necessary, but not wasteful.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's broad aggregate scope, the description is remarkably complete: it lists all return components, provides the correct reading of those numbers, warns about data freshness in demo mode, and explicitly states exclusions. The existence of an output schema further reduces the need to describe return shapes, so this description fully equips an agent.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool has zero parameters, so the baseline is 4. The description effectively explains what the no-argument call returns, which is sufficient; there are no parameter details to add.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description opens with 'START HERE for any US natural gas / Henry Hub question' and calls itself 'the whole dashboard in one call,' making its aggregate purpose unmistakable. It clearly distinguishes itself from siblings by stating an agent does not need to chain five tools, and it enumerates exactly what data sections are returned.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly says to start here for any US natural gas/Henry Hub question, and it gives a when-not case: 'Long histories and daily series are deliberately left out; fetch the dedicated tool when you need one.' However, it does not name specific alternative tools, so the guidance stops short of being fully explicit about which sibling to choose.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
get_us_natural_gas_news_contextARecent events moving US natural gas: LNG plant outages and restarts, Gulf storms, and market-wide stories, each with its source link. Pro scope adds our reading of every story — bullish / bearish / neutral, a 1-5 strength score explicitly gated on whether the story reaches Henry Hub (US liquefaction runs near its ceiling, so foreign demand shocks often move JKM and TTF but not the domestic balance) and whether it is already priced in, plus machine-readable facts (plant, status, Bcf/d, dates) and a plain-English summary. Demo scope returns the same reading for stories older than a week and headlines for the fresh ones.
| Name | Required | Description | Default |
|---|---|---|---|
| days | No | Look-back window in days for events to consider. | |
| limit | No | Maximum number of events to return, newest first. |
| Name | Required | Description |
|---|---|---|
| asof | No | |
| data | No | |
| note | No | |
| tool | No | |
| scope | No | |
| stale | No | |
| disclaimer | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description goes well beyond the annotations (readOnlyHint, openWorldHint, idempotentHint) by detailing the Pro and Demo scopes, the gating logic for bullish/bearish/neutral ratings, strength scores tied to Henry Hub relevance and pricing, and machine-readable facts. This provides rich behavioral context that annotations alone cannot convey.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is appropriately detailed for a tool that returns complex news context with analysis, but it is somewhat lengthy. The key information (purpose and scope behaviors) is front-loaded, and every sentence adds value. It could be slightly more concise without losing clarity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the existence of an output schema, the description does not need to elaborate on return values. It explains the Pro and Demo scopes well but fails to clarify how a user or agent can control which scope is returned (e.g., is it based on authentication, a separate parameter, or default?). This is a minor gap, but overall the description provides sufficient context for an agent to understand the tool's behavior.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema covers both parameters (days and limit) with descriptions, resulting in 100% schema description coverage. The tool description does not add significant meaning to these parameters beyond what the schema already provides. It discusses output behavior involving scopes, but no scope parameter is defined, which may cause some confusion. Baseline score is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states what the tool does: it returns recent events moving US natural gas such as LNG plant outages, Gulf storms, and market-wide stories, each with its source link. The verb 'get news context' is implied, and the function is easily distinguished from sibling tools that focus on chart, storage, production, etc., which are more data-specific.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for obtaining news context but does not explicitly state when to use this tool over alternatives or provide exclusionary guidance. However, given the sibling tools' names, it is clear this is the go-to for news, and the description gives enough context to infer appropriate use cases.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
get_us_natural_gas_pressure_summaryAOur reading of every US natural gas fundamental in one call: for each factor — LNG feedgas, LNG plant outages, weather-model shifts, the EIA weekly injection pace, the composite fundamental score and its 30-day trend, power burn against normal and NOAA cooling demand — the direction of pressure on Henry Hub (bullish / bearish / neutral), its strength (moderate / strong), the number driving it with the thresholds used, and a plain-English sentence. Ends with an overall roll-up: the score, the signals pushing it down and up with their contributions, and any strong factor sitting outside the score. Direction is the sign of a deviation from normal, not a probability that price moves. Demo scope returns the same shape on delayed data.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
| Name | Required | Description |
|---|---|---|
| asof | No | |
| data | No | |
| note | No | |
| tool | No | |
| scope | No | |
| stale | No | |
| disclaimer | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description adds detail beyond annotations, explaining the output includes direction, strength, and plain-English sentences. It clarifies that direction is deviation from normal, not price probability. No contradiction with annotations (readOnlyHint, idempotentHint).
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single long sentence with many clauses, making it dense and somewhat run-on. It front-loads the main purpose but could be more concise and structured.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity and multiple factors listed, no parameters, and presence of output schema, the description is sufficiently complete for an agent to understand the tool's purpose and output.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
No parameters exist, so schema coverage is 100%. Baseline 4 applies as description does not need to add parameter info.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it provides a summary of US natural gas fundamentals, listing specific factors and their impact on Henry Hub. It distinguishes itself from sibling tools like get_us_lng_feedgas or get_us_natural_gas_storage_nowcast by being a comprehensive roll-up.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for a comprehensive overview but lacks explicit when-to-use or when-not-to-use guidance. It mentions demo scope but no alternatives or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
get_us_natural_gas_production_nowcastADaily/monthly US dry natural gas production nowcast (Bcf/d), estimated from the year-ago level scaled by a YoY growth trend and anchored to news, with a per-month series (est vs EIA actual once published). Demo scope hides the freshest month's estimate.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
| Name | Required | Description |
|---|---|---|
| asof | No | |
| data | No | |
| note | No | |
| tool | No | |
| scope | No | |
| stale | No | |
| disclaimer | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond the annotations (readOnlyHint, non-destructive), the description discloses important behavioral traits: the estimation method, the data structure ('per-month series (est vs EIA actual once published)'), and a critical limitation ('Demo scope hides the freshest month's estimate'). This is substantial contextual information not captured in 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.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences, front-loaded with the core purpose and units, and every clause adds value. It efficiently conveys the methodology, data series, and demo limitation without redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the absence of parameters and the presence of an output schema (not shown to the agent), the description is remarkably complete. It explains the frequency, units, estimation basis, and a key limitation. It leaves no major ambiguity about what data will be returned.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool has zero parameters, so the schema carries no semantic burden. Per calibration baseline, a tool with 0 params receives a 4. The description does not need to explain parameters; it correctly focuses on the output and methodology.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states that the tool provides a 'Daily/monthly US dry natural gas production nowcast (Bcf/d)' with specific methodology ('estimated from the year-ago level scaled by a YoY growth trend and anchored to news'). This is specific and distinguishes it from sibling tools like storage nowcast or weather models.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit guidance is given about when to use this tool versus alternatives. The description explains what the tool does but does not mention any alternative tools or exclusion criteria, leaving the agent to infer usage context from the tool name alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
get_us_natural_gas_storage_nowcastAEIA weekly natural gas storage report (Bcf, lower-48 working gas): the
released headline injection/withdrawal plus, on pro scope, pending —
our estimate of the report that has NOT been published yet, built from
weather-driven demand and LNG feedgas components — and
last_verified (estimate vs actual with realized error), alongside
out-of-sample accuracy and backtest stats. Demo scope returns only the
already-published actual.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
| Name | Required | Description |
|---|---|---|
| asof | No | |
| data | No | |
| note | No | |
| tool | No | |
| scope | No | |
| stale | No | |
| disclaimer | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond the annotations (readOnly, openWorld, idempotent, non-destructive), the description discloses important behavioral traits: the `pending` field is an estimate of a not-yet-published report, built from weather-driven demand and LNG feedgas components, and `last_verified` includes realized error. It also explains that demo scope only returns published actuals. This is rich, non-contradictory context.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is dense but every clause carries substantive information: the data source, unit, scope, components of the nowcast, error tracking, and demo behavior. It is front-loaded with the core purpose and uses efficient punctuation to pack detail without becoming unreadable. No wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Despite having no parameters and an existing output schema, the description fully explains what the tool returns in both scopes, the nature of the nowcast, and the associated accuracy metrics. For a read-only information tool with an output schema, this level of description is complete and leaves no major ambiguity about when or how to use it.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool has zero parameters and the input schema is empty, so the baseline is 4. The description adds no parameter-specific meaning because there are none, but it compensates by explaining output scope (pro vs. demo) and the nature of returned fields, which is valuable for an agent deciding how to interpret results.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly identifies the tool as returning the EIA weekly natural gas storage report, specifically the released headline injection/withdrawal and, on pro scope, a pending nowcast estimate. It distinguishes from sibling tools by naming the storage report and its lower-48 working gas context, and explicitly says 'Demo scope returns only the already-published actual.' This is specific and unambiguous.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides clear context for when to use the tool: to obtain the EIA weekly storage report and a nowcast for unpublished reports. It explains scope-dependent behavior (pro vs. demo), which helps the agent decide based on expected output. It does not name alternatives explicitly, but the context is sufficient and no misleading guidance is present.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
get_us_natural_gas_weather_modelsAWeather forecasts that drive US natural gas demand: 7-day population-weighted CONUS cooling and heating degree days from the GFS and ECMWF runs, the change versus the previous day's run, the GFS-ECMWF spread, the per-day degree-day profile, and the latest NOAA CPC forecast revision with its percentile. Full data on both scopes.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
| Name | Required | Description |
|---|---|---|
| asof | No | |
| data | No | |
| note | No | |
| tool | No | |
| scope | No | |
| stale | No | |
| disclaimer | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false. The description adds context about the data content (e.g., change versus previous day, GFS-ECMWF spread) beyond what annotations provide. No contradiction.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two concise sentences with no wasted words. The key information is front-loaded, covering the purpose and data details efficiently.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no parameters and the existence of an output schema, the description is complete. It explains what the tool returns (degree days, profiles, forecasts) without needing further elaboration.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
There are zero parameters in the input schema, and schema coverage is 100% (trivially). The description compensates by detailing the specific data fields returned, adding meaning beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it provides weather forecasts driving US natural gas demand, listing specific data points (cooling/heating degree days, GFS, ECMWF, CPC). It distinguishes from sibling tools by focusing on weather models rather than other data like Henry Hub or LNG.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for weather data affecting natural gas demand, but it does not explicitly state when to use this tool versus alternatives or provide exclusions. No guidance on when not to use it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Claim this connector by publishing a /.well-known/glama.json file on your server's domain with the following structure:
{
"$schema": "https://glama.ai/mcp/schemas/connector.json",
"maintainers": [{ "email": "your-email@example.com" }]
}The email address must match the email associated with your Glama account. Once published, Glama will automatically detect and verify the file within a few minutes.
Control your server's listing on Glama, including description and metadata
Access analytics and receive server usage reports
Get monitoring and health status updates for your server
Feature your server to boost visibility and reach more users
For users:
Full audit trail – every tool call is logged with inputs and outputs for compliance and debugging
Granular tool control – enable or disable individual tools per connector to limit what your AI agents can do
Centralized credential management – store and rotate API keys and OAuth tokens in one place
Change alerts – get notified when a connector changes its schema, adds or removes tools, or updates tool definitions, so nothing breaks silently
For server owners:
Proven adoption – public usage metrics on your listing show real-world traction and build trust with prospective users
Tool-level analytics – see which tools are being used most, helping you prioritize development and documentation
Direct user feedback – users can report issues and suggest improvements through the listing, giving you a channel you would not have otherwise
The connector status is unhealthy when Glama is unable to successfully connect to the server. This can happen for several reasons:
The server is experiencing an outage
The URL of the server is wrong
Credentials required to access the server are missing or invalid
If you are the owner of this MCP connector and would like to make modifications to the listing, including providing test credentials for accessing the server, please contact support@glama.ai.
No comments yet. Be the first to start the discussion!
