NatGasLens — US Natural Gas & Henry Hub Data

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

Annotations already establish readOnly/idempotent/non-destructive behavior. The description adds meaningful operational context: the data is weekly, combines futures and options, and lags the market, with `days_stale` quantifying the lag. This goes beyond what annotations provide.

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 dense sentences, front-loaded with the resource and metric list, followed by the critical staleness caveat. Every sentence adds value and nothing repeats the title or annotations.

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?

For a parameterless, read-only tool with an output schema, this description is nearly complete: source, metric set, combination scope, and staleness are all covered. The only slight ambiguity is the phrase 'both scopes,' which is not expanded, though the output schema likely clarifies 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, so the schema fully covers parameter semantics and the baseline is 4. The description instead explains the contents of the output, which is appropriate here since there are no parameters to elaborate on.

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 names a specific resource (Henry Hub CFTC COT positioning), a clear source (weekly CFTC Commitment of Traders report), and enumerates the exact metrics returned. This makes it obvious how it differs from sibling tools like forward curves, storage, weather, or production.

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 clearly implies the tool is for speculative positioning data from CFTC COT, so an agent can infer when it is relevant. It does not explicitly name alternatives or state when-not-to-use cases, though the uniqueness of the data makes this a minor gap.

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

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

Annotations already signal a safe, idempotent read operation, and the description adds the Pro-scope behavior (live prices and curve-shape read) plus a not-investment-advice disclaimer. This supplements the structured metadata without 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.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded with the core purpose and stays informative without excessive length. The additional Pro-scope and disclaimer sentences earn their place by clarifying expected behavior.

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 a single optional parameter, complete schema coverage, a rich output schema, and annotations covering safety/idempotency, the description provides all needed context. Nothing critical is missing.

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 only parameter, months, is fully documented in the schema with a clear description. The tool description adds no new parameter detail, so schema coverage carries the burden.

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 names a specific resource (Henry Hub natural gas futures forward curve) and details exactly what is returned: price, session move, volume, and prior-year comparisons. This clearly differentiates it from sibling tools about storage, weather, and production.

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 content makes it obvious this is the tool for forward-curve data, but there is no explicit when-to-use guidance or comparison with siblings. Usage is implied rather than stated.

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

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

This goes well beyond the readOnly/idempotent annotations by revealing the nowcast nature, the fragmented data source ('split across operators, no single public source'), the difference between measured and estimated values, the Pro/Demo access scope, and how the regime label is computed. No annotation conflict exists.

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 every sentence contributes unique operational detail: data source, return fields, regime definition, Pro scope, and Demo scope. It is front-loaded with the core identity of the tool and avoids filler, making it dense but efficient.

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 complexity, the presence of an output schema, and rich annotations, this description is complete. It explains the data provenance, what the return contains, how the regime label is determined, what Pro vs Demo scope changes, and the single parameter's role. Nothing essential for selecting or invoking the tool is missing.

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?

With only one optional parameter and 100% schema description coverage ('How many days of daily feedgas history to return (1-400)'), the schema already fully documents the parameter. The description mentions daily history but does not need to add further parameter details; the baseline of 3 applies.

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 a specific verb-plus-resource ('Daily LNG feedgas for US liquefaction terminals') and clearly enumerates what is returned: today's total, regime label, utilization, and daily history. It naturally differentiates itself from siblings such as get_us_lng_plant_outages by focusing on the export pull on the domestic gas balance rather than outages or production.

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 does not explicitly name alternative tools or state 'use this instead of X', but it provides strong contextual signals: it is the feedgas nowcast tool, sourced from pipeline nominations, and appropriate whenever LNG terminal feedgas or export pull is the subject. The Pro/Demo scope explanation also clarifies what level of detail a caller can expect, though it does not list exclusions.

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

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

Beyond the annotations, the description discloses a meaningful behavioral trait: status is automatically inferred using pipeline data first and news second, and each record identifies the deciding source. It also explains the Pro/Demo scope differences, adding real context beyond structured 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 compact yet information-dense, with each sentence adding distinct value: output contents, inference method, and scope limitations. It is well-structured, front-loading the core purpose before secondary details.

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?

For a parameterless read-only tool with an output schema, the description thoroughly covers what data is included, how status is derived, and how scopes differ. There is no obvious missing information an agent would need to select and invoke this tool correctly.

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 there are no parameter semantics to clarify. The description compensates well by explaining output scope and data-source behavior, meeting the baseline expectation for a parameterless tool.

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's purpose: reporting operating status for US LNG export plants with specific metrics like flow vs. nameplate and offline capacity. It differentiates from its siblings by its focus on plant outages/status, but does not explicitly name or contrast a sibling tool.

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?

It provides clear context on what the tool returns and includes useful scope distinctions ('Pro scope adds...', 'Demo scope lags 7 days'). It does not explicitly state when to choose this tool over sibling tools, but the purpose is specific enough that an agent can infer appropriate use.

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

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

Annotations already mark the tool as read-only/idempotent, but the description adds meaningful behavior: it returns a PNG image, it is the same card published to their own channel, and it requires a token because demo scope cannot serve charts delayed. This gives the agent operational and authentication context beyond the structured 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 front-loaded with the core identity and output type, followed by a clear usage directive and the kind list. It is slightly longer than necessary because the kind list repeats the schema, but each sentence carries functional information and none are filler.

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?

For a simple one-parameter chart tool with no output schema, the description is complete: it states the output format, enumerates available chart kinds, explains when to use it versus data tools, and notes auth requirements. Nothing an agent needs to decide whether to invoke this tool is missing.

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 schema already fully describes the single kind parameter, including all allowed values and the default. The description repeats the same enum list without adding new parameter-level meaning, so it does not substantially exceed the schema coverage.

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 identifies a specific resource (US natural gas chart), the output format (PNG), and the concrete chart contents (LNG feedgas, storage, weather runs, etc.). It also separates this chart tool from the data-returning sibling tools by explicitly saying the numbers are available as data from other tools.

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?

It explicitly says to use the chart when a human is going to look at the answer, and directs agents to other tools for the underlying data. The token/demo-scope constraint adds a clear prerequisite and limitation, which is valuable for deciding whether this tool is usable in a given context.

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

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

Annotations already mark this as read-only and idempotent, and the description adds significant behavioral context beyond that: it ALWAYS returns out-of-sample accuracy and a disclaimer, demo scope returns a delayed score without breakdown, and include_history defaults off due to length. There is no contradiction with 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 dense but well organized: the core purpose is front-loaded, followed by mandatory return behavior, then the optional parameter and scope variation. Every sentence contributes useful information, and there is no redundant filler.

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?

For a tool with one optional parameter, an output schema, and read-only/idempotent annotations, the description is essentially complete. It explains the score's construction, output components, accuracy reporting, disclaimer, history option, and demo-scope caveat, so an agent has enough to invoke it correctly.

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 sole parameter include_history is already fully documented in the input schema, including its default, its effect, and why it is off by default. The description repeats that information and adds demo-scope nuance, but the schema already carries most of the parameter-meaning burden, so the 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 identifies the resource and purpose: a composite fundamental pressure score for US natural gas/Henry Hub on a -100..+100 scale, built from five named signals, and followed by the output components like per-signal breakdown, percentile, and NOAA forecast revision. It distinguishes itself from sibling tools by describing unique output content, but it does not explicitly contrast itself with similar-sounding siblings such as get_us_natural_gas_pressure_summary.

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 offers useful context about optional history and demo-scope behavior, but it does not explicitly state when to choose this tool over alternative market-data tools. There is no when-to-use/when-not-to-use guidance or mention of sibling tools, so the usage guidance is mostly implied rather than explicit.

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

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

Beyond the readOnly/idempotent annotations, it discloses the data-as-of condition, demo-scope delayed data, the fact that pressure direction is a deviation sign not a price probability, and the interpretation rules embedded in `note`. This materially changes how an agent should consume the result.

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?

Despite its length, it is front-loaded with the core directive and the one-call value proposition, then organized into numbered return groups and caveats. Each sentence earns its place, providing dense specification without fluff.

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 enumerates all returned components, explains the reading rules that prevent common misuses, names the data that is deliberately excluded, and notes demo behavior. With an output schema also present, this is fully complete for an agent to select and call it correctly.

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 already exhausts the input contract and the baseline for empty-parameter tools is 4. The description does not need to explain any parameter syntax; it adds value by explaining what the single call returns.

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?

Opens with 'START HERE for any US natural gas / Henry Hub question' and names the exact resource: the whole dashboard in one call. It also distinguishes itself from the dedicated sibling tools by noting that long histories and daily series are deliberately left out.

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 tells the agent when to start with this tool ('START HERE') and why it beats chaining five aggregating tools. It also gives a clear when-not-to-use signal: when long histories or daily series are needed, fetch the dedicated tool instead.

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

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

Annotations already declare read-only, open-world, idempotent, and non-destructive behavior. The description adds detail about the scoring logic (gating on Henry Hub relevance and whether events are priced in) and the output variations between scopes, which goes 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 somewhat verbose and rambling, with a lengthy parenthetical about Henry Hub and JKM/TTF that could be condensed. However, it is still structured logically and conveys all key information without being excessively long.

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 explains what the tool returns for both Pro and Demo scopes, including the type of analysis (bullish/bearish/neutral, strength score) and additional facts. Since no output schema is provided, this description compensates well by outlining the expected output structure.

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 schema provides complete descriptions for both parameters (days and limit) with ranges and defaults. The description does not add any extra meaning to these parameters, so the baseline of 3 is appropriate given the 100% schema coverage.

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 tool's purpose: retrieving recent events affecting US natural gas, including specific types (LNG outages, Gulf storms, market stories) and that each event includes a source link. The resource and action are 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 does not explicitly state when to use this tool over sibling tools. It explains the difference between Pro and Demo scopes but offers no guidance on selecting this tool vs. others like get_us_natural_gas_market_brief or get_us_natural_gas_fundamental_score.

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

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

Annotations already indicate a safe read-only, idempotent operation, and the description adds substantial behavioral context: the output includes per-factor direction, strength, count and thresholds, a plain-English sentence, an overall roll-up, and the demo-scope behavior. It also guards against misinterpretation by stating that direction reflects deviation from normal, not price probability.

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 a clear one-line summary and then adds needed detail about outputs, interpretation, and demo behavior. It is fairly long but each clause contributes useful semantics; a small amount of trimming could tighten the factor list 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?

For a complex aggregated report tool, the description is thorough: it covers the covered factors, the output structure, the direction interpretation caveat, and demo-scope behavior. With zero parameters, a rich output schema, and clear annotations, nothing essential is missing for an agent to select and invoke the tool correctly.

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 has no parameter gaps to compensate for. The description does not discuss parameters because none exist, and it clarifies what the no-argument call returns, which is enough for this dimension.

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 a specific verb-resource pairing: 'our reading of every US natural gas fundamental in one call.' It then enumerates the covered factors, making clear that this is a comprehensive aggregation tool rather than a single-factor sibling like get_us_lng_feedgas or get_us_natural_gas_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?

The description clearly conveys that this is a one-call overview of all fundamentals, which implies it is the aggregate choice among the single-factor sibling tools. However, it does not explicitly state when not to use it or name alternatives, so it stops short of full routing guidance.

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

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

Annotations already signal readOnly/openWorld/idempotent/non-destructive. The description adds valuable behavioral context: the estimation method, the est-vs-EIA series, and the demo limitation that the freshest month's estimate is hidden. This goes well beyond what annotations 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?

Two dense sentences with no filler. The main purpose is stated first, followed by methodology and the demo caveat. Every clause contributes useful information for invoking or interpreting the tool.

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 zero parameters and the presence of an output schema, the description covers all necessary invocation context: units, frequency, series semantics, estimation approach, and the demo limitation. Nothing essential for a correct call is missing.

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?

With zero parameters, there is no parameter ambiguity to resolve. The description adds no parameter-specific meaning because none exists; the baseline for a no-parameter tool applies and is fully satisfied.

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 identifies the tool as retrieving US dry natural gas production nowcasts in Bcf/d, with daily/monthly granularity. The methodology (YoY trend scaled from year-ago level, anchored to news) and comparison to EIA actuals further distinguish it from sibling nowcast tools like storage or 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?

The description makes it obvious when to use this tool: whenever a production nowcast is needed, vs. storage/weather/market brief siblings. It does not explicitly list exclusions or alternative tools, but the domain-specific phrasing provides clear context for a zero-parameter retrieval tool.

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

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

Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, and destructiveHint=false, covering the safety profile. The description adds significant behavioral context: the presence of 'pending' estimates, 'last_verified' error stats, out-of-sample accuracy, backtest stats, consensus snapshot, and surprise calculation. It also differentiates between pro and demo scopes, which is not in annotations. This is valuable additional transparency beyond the structured data.

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 dense paragraph but is front-loaded with the core purpose and then elaborates on components. Every sentence adds information about data contents or scope behavior. It could be slightly more scannable with bullet points, but it is efficient and not redundant.

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 has no parameters and an output schema exists (per signals), the description need not explain return values. It adequately covers scope differences, data components, and the distinction between nowcast and consensus. It is complete for an agent to call correctly, though it could mention rate limits or data freshness, but that is minor.

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 is trivially complete (100% coverage). Per the rubric, 0 parameters gives a baseline of 4. The description enhances this by detailing the output fields (consensus_bcf, actual_minus_consensus_bcf, est_bcf, etc.) and their meanings, adding semantic value beyond the empty 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 starts with a precise verb+resource: 'EIA weekly natural gas storage report (Bcf, lower-48 working gas)'. It clearly distinguishes itself from siblings by focusing on storage nowcast data, including actual, estimate, consensus, and surprise. The scope ('pro' vs 'demo') is explicitly defined, making the tool's 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 provides clear context on when to use it: it covers both published actuals and pending estimates, with a note that 'demo scope returns only the already-published actual'. It also clarifies that `est_bcf` is a model nowcast, not the consensus, which helps avoid misuse. However, it does not explicitly name alternative tools or state conditions to prefer a sibling, so it loses one point.

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

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

Annotations already declare the tool read-only, idempotent, and non-destructive. The description adds useful behavioral context by enumerating the data fields, including the previous-day-run change, model spread, and CPC percentile. It explains what kind of data the agent will receive without relying on the output schema alone.

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 dense sentence that packs substantial detail into a compact form. It front-loads the core purpose and then lists the included data elements. The phrase 'Full data on both scopes' is slightly ambiguous, but overall the description is efficient with no filler.

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?

For a parameterless read-only tool with an output schema and rich annotations, the description provides strong context about the data contents, model sources, and derived metrics. The slight ambiguity around 'both scopes' and the lack of any temporal or update-frequency context prevent a perfect score.

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 there are no parameter semantics to document. The schema description coverage is complete by default, and the baseline for parameterless tools is 4 because the description rightly focuses on the returned data rather than input options.

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 a specific resource: US natural gas demand weather models, listing exactly which datasets are included (7-day population-weighted CONUS degree days, GFS/ECMWF runs, spread, per-day profile, CPC revision). This differentiates it well from sibling tools focused on storage, production, LNG, or market data.

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 when this tool is relevant by stating it covers 'weather forecasts that drive US natural gas demand,' but it does not explicitly say when to use it versus alternatives like market briefs or fundamental scores. The usage context is clear but no exclusions or routing guidance is provided.

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