SiteCheck Trade & Energy

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

Annotations only declare readOnly and openWorld; the description adds genuinely non-obvious behavior: the result set is capped at the newest 12 tenders, fetching requires a rendering residential proxy, and each successful call costs $0.02 in USDC via x402 on Base/Solana/Arc with failed calls free. The cost and freshness-cap facts materially affect an agent's decision to call 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?

Front-loaded with the core identification and scope, followed by a compact field list and a payment-model sentence. Dense but every clause carries information; only the field enumeration brushes against redundancy with the output schema.

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?

An output schema exists, so return-field enumeration is somewhat redundant, but coverage is otherwise complete: source, freshness cap, filters, and billing model are all present. Nothing an agent needs to invoke it correctly 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?

Schema coverage is 100%, and both parameters already carry examples in the schema ('water, road, solar'; 'Pakistan, Bangladesh'). The description only restates that keyword and country filtering exist without adding format, matching, or partial-match semantics, so it stays at the baseline.

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?

States a specific verb+resource: Asian Development Bank procurement notices, with scope (newest 12 tenders) and the returned fields enumerated. The source (adb.org/projects/tenders) implicitly distinguishes it from energy_world_bank_procurement and energy_inter_american_dev_bank, but no sibling is named explicitly.

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?

Says the results are 'optionally filtered by keyword and country', which hints at usage, but gives no explicit when-to-use guidance and never mentions the World Bank or IDB procurement siblings an agent might reasonably confuse it with. 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?

Annotations already carry readOnlyHint and openWorldHint, so the safety profile is covered. The description adds genuinely non-obvious behavior: a paid x402 call at $0.002 USDC with settlement on Base, Solana or Arc, and that failed calls are not charged — material cost information an agent must know before invoking.

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?

Content is front-loaded with identity and search capability, then the return payload, then pricing. It is a single dense block rather than scannable sentences, but every clause carries information; nothing is padding.

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, spelling out return fields is mild redundancy, but the description supplies the pieces structured data cannot: billing model, payment rails, and failure-charge policy. What is missing is sibling routing against the other carbon registries in this toolset.

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%, so the baseline is 3. The description earns above baseline by decoding the type-code parameter conceptually (forest carbon, landfill gas, refrigerants, orphaned wells, CCS), which the schema only exposes as bare abbreviations like FC, LGCC, REF and ORW.

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?

States a specific verb+resource: searching ACR project records on ICE GreenTrace by text or project type, and enumerates the returned fields. It is clearly distinct from siblings by registry identity (ACR), though it never names the adjacent registries (Verra, Gold Standard, Climate Action Reserve) that an agent might confuse it with.

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?

Usage is only implied: 'search by text or project type' plus example project types tells the agent how to call it, but there is no guidance on when to choose this registry versus the sibling carbon-registry tools, nor any statement of exclusions or prerequisites.

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 and openWorld annotations, the description discloses the data source, update frequency, and crucial limitations: the values are indexes rather than spot prices and exclude Gulf/Tampa quotes. It also adds important billing behavior, including the per-call cost and the fact that failed calls are not charged.

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 data identity, followed by the most important caveat and then pricing. Every sentence adds distinct value, and there is no redundant or filler language.

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 single-parameter data retrieval tool with an output schema and safety annotations, the description supplies the remaining context an agent needs: the source, the nature of the values, exclusions, and cost. Nothing essential for correct selection or invocation appears to be 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 its range and default. The description does not add any parameter-specific semantics, so the schema carries the meaning and the baseline score of 3 is appropriate for high 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 states a specific resource and scope: monthly US producer price indexes for ammonia and nitrogen fertilizer from BLS via FRED. It also distinguishes the data from spot prices by explicitly saying these are index values, not USD spot quotes.

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 signals when not to use the tool by excluding USD spot prices and US Gulf/Tampa spot quotes, which helps route the agent away from spot-price use cases. However, it does not explicitly name alternative tools or spell out the exact conditions under which this tool should be selected over other energy data tools.

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?

With only readOnlyHint and openWorldHint annotations, the description adds substantial behavioral context: perfect foresight, one full cycle per day, no grid fees or degradation, round-trip losses, and gross margin as an upper bound. It also discloses pricing and that failed calls are not charged, which is important operational behavior not present in 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 definition is front-loaded with the metric and scope, then gives assumptions and pricing in compact sentences. Despite being dense, every sentence adds useful selection or interpretation context.

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 covers market, metric definition, assumptions, limitations, parameter options, and payment behavior, while the output schema can carry return-value details. It is complete enough for an agent to decide whether and how to call the 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?

Schema description coverage is 100%, so the input schema already documents date, efficiency, and durationHours with defaults and ranges. The description reinforces the 1/2/4-hour options and 88% default efficiency, but adds little beyond the schema and does not add further syntax or constraints.

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 states a specific computed metric and market context: daily battery storage arbitrage margin on EPEX SPOT DE-LU hourly prices, including charging/discharging hours, spread, and gross margin per MW. It clearly distinguishes this derived BESS screening tool from raw power-price siblings.

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 gives clear usage context by calling the result an upper-bound screening number and explicitly not a trading result. It does not name a specific sibling alternative, such as the raw EPEX spot price tool, so it stops short of full when-to-use/when-not-to-use 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 cover read-only and open-world behavior, and the description adds real context beyond that: monthly refresh cadence, the $0.002 USDC cost per successful call via x402 (Base/Solana/Arc), and that failed calls are not charged. It stops short of describing pagination or row ordering behavior beyond the newest-first hint in the schema.

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?

Front-loaded with the source and datasets, then closes with filtering, freshness and cost. The opening sentence is dense but every clause carries information; the pricing sentence is compact and purposeful.

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, return shape needn't be described, and read-only/open-world annotations cover safety. The description supplies source, scope, filters, refresh cadence and cost model — enough for correct invocation; only ordering/pagination semantics stay implicit in the schema.

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%, so baseline is 3; the description still adds value by mapping the declared report values to actual data families (prices, trades, generation, generation-monthly) and clarifying that D codes span D3-D6 in the data while the schema allows D7.

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?

States a specific verb+resource: pulls US EPA RFS (EMTS) RIN data, and enumerates exactly which datasets (weekly VWAP prices of D3-D6, trade volumes, generation by D code, monthly generation by producer type). This clearly distinguishes it from nearby carbon-credit siblings such as energy_rggi_carbon_allowance or energy_verra_vcs_registry.

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?

Usage is implied by the dataset enumeration and the 'filter by D code and year' note, plus the freshness cue 'EPA refreshes it monthly'. However there is no explicit when-to-use/when-not framing and no named alternative among the many energy-credit siblings, so selection still requires inference.

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?

Goes well beyond readOnlyHint/openWorldHint by disclosing the pricing model ($0.002 USDC per successful call, x402 on Base/Solana/Arc) and that failed calls are not charged — a real cost/risk signal for the agent. It also states result ordering (latest months first) and that values are as published.

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?

Four tight clauses: what it is, format/ordering, scope caveat, price. The critical identifying information is front-loaded and nothing is 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?

With an output schema present, the description needn't explain return structure; it covers source, unit, ordering, coverage caveat and cost. Nothing an agent needs to call this correctly 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?

Schema coverage is 100%, so baseline is 3, but the description adds real meaning beyond the schema: 'for one country' clarifies that country selects a single series, and 'latest months first' explains how the months parameter is applied.

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?

Names the exact resource (BIS nominal broad effective exchange rate), the entity scope (one country), the unit/format (monthly index values, base 2020 = 100) and the source API. It also disambiguates from bilateral rates, so an agent can tell what family of data this is without opening the schema.

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 'not a bilateral rate' and 'broad basket of 64 economies' notes give context for selection, but there is no explicit when-to-use/when-not or any named alternative among the many sibling tools. Usage is implied rather than routed.

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 cover the safety profile (readOnlyHint). The description adds genuinely useful non-obvious context: precise pricing ($0.002 USDC per successful call via x402 on Base/Solana/Arc) and the important fact that failed calls are not charged. Data freshness (5-minute granularity, 'so far') is also disclosed.

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?

A single dense sentence, front-loaded with what the tool returns and followed by pricing. Every clause carries operational meaning (data sources, granularity, forecast types, cost); nothing is 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?

With an output schema present, the enumeration of returned fields in the description is somewhat redundant, but pricing and freshness fill the real gaps. For a zero-parameter, read-only, output-schema-backed tool, the agent has enough to 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 takes zero parameters, so the baseline is 4. There is nothing for the description to clarify about inputs.

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?

States a specific verb+resource: 'CAISO grid today, from its Today's Outlook data', then enumerates exactly which data streams are returned (5-minute generation by source, demand with forecasts, net load, peaks). This is clearly distinguishable from grid siblings like energy_ercot_texas_grid_status or energy_miso_midcontinent_iso.

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?

Usage is implied by 'today' and '5-minute intervals so far', so an agent can infer this is a current-day snapshot tool. However, no alternative is named for historical CAISO data or for other ISOs, and no when-not condition is 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?

Beyond the readOnlyHint/openWorldHint annotations, it discloses the paid-call model ($0.002 USDC per successful call via x402 on Base, Solana or Arc) and that failed calls are not charged — genuinely decision-relevant for an agent. It stays consistent with readOnlyHint. It does not add rate limits or result-shape caveats, but the cost disclosure is a real value add over 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?

Front-loaded with the registry and source before the field list and filters, then a separate sentence for pricing. The field enumeration is long but each item is substantive; slightly denser than necessary but no filler 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?

An output schema exists, annotations cover the read-only/open-world profile, and the schema documents every parameter, so the description need only supply sourcing, cost and sort semantics — which it does. The one missing piece is explicit sibling disambiguation between CAR and the other carbon registries.

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 100% schema description coverage, the schema already documents all seven parameters including examples. The description only restates the filter dimensions (type, status, state, country, text) and adds one fact not in the schema — results are sorted by credits. Baseline 3 is appropriate when the schema carries the parameter detail.

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?

Specific verb+resource ('Carbon offset projects registered with the Climate Action Reserve') plus the upstream source (public APX project report) and an enumeration of returned fields. The explicit naming of CAR as the North American voluntary and California compliance registry implicitly separates it from energy_american_carbon_registry, energy_verra_vcs_registry and energy_gold_standard_credits.

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 the usage context clear — browse/filter CAR project records by type, status, state, country or text, sorted by credits. It does not explicitly state when to prefer this over the sibling registries (ACR/Verra/Gold Standard), so there is clear context but no 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?

Annotations already cover read-only and open-world behavior, yet the description still adds real value: a paid-call model ($0.002 USDC per successful call via x402 on Base, Solana or Arc) and the explicit guarantee that failed calls are not charged. It also discloses source and monthly cadence, though it omits refresh latency or rate limits.

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?

Three sentences, front-loaded with the actual data identity before the pricing note and the name-disambiguation caveat. The 'name is kept for the owner's route' clause is slightly inside-baseball but earns its place as a naming warning.

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 single-optional-param read with an output schema, this covers identity, units, source, cadence, history depth and the payment model. Only minor gaps remain, such as refresh frequency and whether values are nominal USD.

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% and the single 'months' parameter is fully documented there, including the 1–24 range and default of 3. The description only echoes the 24-month ceiling, adding no new meaning; 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?

Names the specific resource (monthly world reference prices for corn, wheat, soybeans), the source (FRED / World Bank series, USD) and the payload shape (latest value plus up to 24 months of history). It also explicitly negates the misleading tool name by stating these are not CME futures quotes, so an agent can distinguish it from futures-style siblings at a glance.

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 'not CME futures quotes' line implicitly steers an agent away from futures tools, and the data-source disclosure implies when this is the right choice (World Bank reference prices). But there is no explicit when-to-use/when-not-to-use against alternatives such as energy_usda_wasde_crop_reports or energy_ice_coffee_sugar_cocoa, and no prerequisites 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?

Beyond the readOnlyHint and openWorldHint annotations, the description discloses source provenance (FRED/EIA), scope limits (up to 60 trading days, Cushing storage excluded), and pricing behavior ($0.002 USDC per successful call via x402, failed calls not charged). This is unusually complete behavioral context for invocation and cost awareness.

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?

Three compact sentences with no wasted words. The resource and units are front-loaded, followed by history scope, an exclusion, and payment terms, making it easy to parse quickly.

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 read tool with an output schema and annotations already covering safety and openness, the description supplies all remaining essentials: source, units, scope, exclusion, and cost. Nothing material is missing for correct invocation.

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 documents the single 'days' parameter with range and default, giving 100% schema description coverage. The description adds useful nuance by specifying 'trading days' and 'latest value plus up to 60 trading days of history', but it does not add further syntax or edge-case guidance beyond that.

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 the exact resource (daily spot crude oil prices), the two benchmarks (WTI Cushing and Brent), units (USD per barrel), and source (FRED/EIA series). This clearly distinguishes it from sibling tools covering natural gas, weekly petroleum, OPEC monthly reports, and refined fuel bunkers.

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 gives clear context for using the tool: daily spot crude prices, latest value plus up to 60 trading days of history. It also includes an exclusion (Cushing storage levels are not included), which helps prevent misuse, but it does not explicitly name alternative sibling tools for related oil-market data.

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?

Goes well beyond the readOnly/openWorld annotations by disclosing the upstream source (USDM public API), the exact charge ($0.002 USDC per successful call), the payment rails (x402 on Base, Solana, Arc), and that failed calls are free — critical for an agent deciding whether to call. No behavior is contradicted.

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?

Front-loaded with the resource and scope, followed by exclusions and pricing; every clause carries information. Slightly dense in a single long sentence, but nothing is wasted.

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, return values need no explanation; annotations cover safety. The description supplies what those fields cannot — data source, geographic granularity limits, and cost model — so an agent can call it confidently.

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%, so both parameters are already documented, including the Tuesday/YYYY-MM-DD format and the FIPS example. The description restates '5-digit FIPS' and 'weekly map date' but adds no format or edge-case detail beyond the schema, so the baseline 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?

States a specific resource (US Drought Monitor county statistics) with exact scope: one county by 5-digit FIPS, one weekly map date, returning percent area in no-drought plus D0–D4 categories. It also explicitly bounds itself ('County level only; crop-specific indices are not included'), which separates it from crop-report siblings.

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?

Context is clear: county-level drought percentages for a single FIPS/date, with the default date behavior implied. It excludes crop-specific indices, steering the agent away from misuse, though it never names the sibling tools an agent should pick instead for crop or non-US data.

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 only declare readOnlyHint and openWorldHint; the description adds material behavior the annotations cannot: per-call cost ($0.002 USDC), the x402 payment rails (Base, Solana, Arc), and the crucial billing rule that failed calls are not charged. It also states the units as published (thousand barrels, thousand b/d, %), which prevents misinterpretation of returned magnitudes.

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?

Three sentences, front-loaded with the source and content inventory, then the temporal/unit contract, then pricing. The long series enumeration is dense but each item earns its place as a coverage claim; only the parenthetical list could be compressed further.

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, return shape need not be explained, and the description still covers source authority, series scope, temporal views, units, and payment mechanics. Remaining minor gaps are publication cadence/lag and whether history weeks are release weeks, but nothing prevents a correct call.

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% — 'weeks' 1-52 with default 4 and the full 'series' list with default-all and raw EIA id support (e.g. WCESTUS1) are already documented in the schema. The description does not add parameter-level guidance (e.g. cost or truncation tradeoffs for large week counts), so it only meets the baseline.

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 the exact dataset (EIA Weekly Petroleum Status Report) and enumerates the covered series — crude/SPR/Cushing/gasoline/distillate/jet/propane stocks, production, imports, exports, product supplied, refinery utilization — plus the derived views (latest week, WoW change, history). That is far more specific than a sibling like energy_opec_monthly_oil_market or energy_crude_oil_brent_wti, though no sibling is named explicitly to sharpen the boundary.

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?

Use is implied by the data inventory (weekly US petroleum balances and demand) and by 'latest week, week-over-week change and recent history', but there is no explicit when-to-use statement, no exclusions, and no pointer to alternatives such as the Brent/WTI spot tool or the OPEC monthly tool. An agent must infer selection from content overlap alone.

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?

Goes well beyond the readOnlyHint/openWorldHint annotations: discloses data provenance (ENTSO-E/SMARD via Fraunhofer ISE Energy-Charts), that a licence string accompanies each answer, and the cost model — $0.002 USDC per successful call via x402 across Base/Solana/Arc, with failed calls uncharged. The billing behavior is exactly the kind of non-obvious trait an agent needs before invoking.

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?

One dense paragraph, front-loaded with what the tool returns before provenance and payment terms. Every sentence carries information, though the pricing clause is a long compound sentence that could be trimmed slightly given it repeats no schema field.

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 needn't explain return shapes, and it still covers units, defaults, data lineage, licensing and cost. For a zero-required-parameter read tool, an agent has everything needed 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?

Schema coverage is already 100%, so the baseline is 3; the description still adds value by specifying flow units and sign convention (GW, positive = import) and the per-neighbour expansion, neither of which appears in the schema. Zone examples in the description are a subset of the schema's list, so that part is redundant.

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?

States a specific verb+resource: day-ahead spot prices in EUR/MWh for named European bidding zones, with optional cross-border physical flows. Scope and units are unambiguous. It does not, however, distinguish itself from overlapping siblings such as energy_epex_spot_power_europe or energy_nord_pool_power_elspot, so an agent must infer the difference from the data-source sentence.

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?

Usage is implied through defaults (date=today, zone=DE-LU) and the optional flows flag, which tells the agent how to call it minimally. There is no explicit statement of when to prefer this over the EPEX or Nord Pool siblings, and no when-not guidance. Adequate but leaves the routing decision to inference.

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 cover read-only and open-world behavior, but the description adds genuinely non-obvious traits: the upstream source (ECHO REST service) and the billing model ($0.002 USDC per successful call via x402 on Base/Solana/Arc, failures not charged). That cost disclosure is material for an agent deciding whether to call. It does not cover rate limits or latency, which keeps it off a 5.

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?

Three sentences, purpose and scope front-loaded, exclusion before the commercial note. The pricing sentence is long and slightly tacked on, but it carries useful decision information rather than 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?

With an output schema present, return-value detail is unnecessary, and the description supplies everything else an agent needs: data source, what granularity is and isn't available, single-state constraint, and full cost terms. Nothing essential to correct invocation 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?

Schema coverage is 100% and the single parameter is fully documented as a 2-letter US state code with an example. The description reinforces the single-state scope but adds no format or validation detail beyond the schema, so this is baseline territory.

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?

Names the specific resource (EPA ECHO enforcement/compliance summary), the scope (one US state), and enumerates exactly what is returned: counts of active facilities, inspections, formal enforcement actions and total penalties. It also states the boundary — facility-level violation lists are not included — which separates it from a detail-level 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?

The scope constraint ('for one US state') and the explicit exclusion ('Facility-level violation lists are not included') tell the agent when this tool is the wrong choice. It stops short of naming a sibling alternative for facility-level data, so routing for that case is left implicit.

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 and openWorldHint, but the description adds genuinely non-structured context: pricing ($0.002 USDC per successful call, paid via x402 on Base/Solana/Arc) and that failed calls are not charged. That billing model is exactly the kind of behavioral trait annotations cannot convey. It stops short of describing response shape or coverage/rate limits, hence not a 5.

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 purpose and data source are front-loaded in the first clause, followed by scope limits and cost. Dense and largely waste-free, though the payment details are packed into one long semicolon-heavy sentence that could be split for faster scanning.

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 single-parameter read tool with an output schema, the description covers source, aggregation semantics, scope exclusions, and cost. The only meaningful omission is guidance on obtaining a facility id when the caller doesn't have one, which matters because facility search is explicitly out of scope.

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, fully described in the schema ('GHGRP facility id, digits only, e.g. 1000001'). The description restates the id and example but adds no new constraint beyond the schema, so baseline 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?

States a specific verb+resource+scope: EPA GHGRP reported emissions for one facility by year, sourced from EPA Envirofacts. The aggregation basis (CO2e summed across gases per year, as published) is stated, which distinguishes it from sector-level or registry-wide siblings like energy_epa_echo_enforcement.

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 gives scope exclusions ('Facility search and sector breakdowns are not included') and the required id form (GHGRP facility id, e.g. 1000001), which implies when it applies. But it never names what to use for facility lookup or sector breakdowns, so the agent must infer alternatives from the sibling list.

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 and openWorldHint=true, so the safety profile is covered. The description adds genuinely useful behavior beyond that: the $0.002 USDC per successful call cost, the x402 payment rails (Base, Solana, Arc), and that failed calls are not charged — a detail an agent needs before deciding to pay.

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 tightly packed sentences: the data scope is front-loaded, and the billing/payment facts follow. Every clause (zone, resolution granularity, volume fields, currency, price, payment rails, failure policy) carries information an agent would otherwise have to guess.

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 and full annotation coverage, the description need not describe return structure, and it correctly focuses on scope, granularity and payment terms. It is essentially complete; only edge behaviors (e.g., what is returned before the noon auction publishes, or data latency) are left unaddressed.

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 description coverage is 100%, so all three parameters are already documented with defaults and formats. The description reinforces what the parameters produce (baseload/peakload vs. hourly vs. quarter-hour periods, EUR/MWh vs. MWh) but adds no new syntax or constraint beyond the schema, which is exactly the baseline-3 situation.

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 verb and resource: 'EPEX SPOT day-ahead electricity auction results' for the DE-LU bidding zone, and enumerates the exact content returned (baseload/peakload prices, plus per-hour and per-15-minute price, buy, sell and traded volumes). This clearly separates it from power-market siblings such as nord_pool_power_elspot, entsoe_transparency_eu or caiso_california_iso, which cover different markets.

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 establishes when this tool applies: Germany-Luxembourg day-ahead auction results for a delivery day, with the DE-LU-only restriction and the default delivery-day behavior made explicit. It does not, however, explicitly route the agent to a sibling when a different zone or market is needed, so the choice among the many energy_* tools is left to inference.

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 readOnlyHint=true and openWorldHint=true, so the safety profile is partly covered. The description adds valuable behavioral context beyond annotations: it is live data from public dashboards, costs $0.002 in USDC per successful call via x402, and failed calls are not charged, which is important for invocation decisions.

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 then lists supported data domains and pricing. It is dense but each piece is relevant to an agent deciding whether to call it; the metric list is long but justified for a multi-metric dashboards 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 the tool's complexity, the description covers source, region, data domains, and payment behavior, while an output schema exists to explain return values. It is largely complete, with only minor missing guidance about how it compares to sibling grid/ISO tools.

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 description coverage is 100%, and the single forecastHours parameter is fully documented in the schema. The description mentions forecast data generally but does not add syntax, default, or usage details for the parameter beyond what the schema already provides, 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?

The description uses a specific verb and resource: live Texas (ERCOT) grid status from ERCOT public dashboards. It enumerates the exact data domains covered, including frequency, demand, load, capacity, reserves, generation mix, prices, and forecasts, so it is clearly distinguishable from other grid-status siblings by region and source.

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 to use it by specifying ERCOT/Texas grid status and listing the metrics available. However, it does not explicitly name alternatives such as energy_us_electric_grid_monitor or other ISO tools, nor does it state when not to use this 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?

Beyond the readOnlyHint/openWorldHint annotations, the description discloses what annotations cannot: the upstream source, the $0.002 USDC cost per successful call, the x402 payment rails (Base, Solana, Arc), and the charge policy that failed calls are free. It also clarifies that criteria are returned as text, which is behavioral detail an agent needs before committing to a paid call.

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, front-loaded with the verb, source and regulation before pricing. The first sentence is long and semicolon-stacked, which slightly hurts scannability, but every clause (source, outputs, scope boundary, cost, payment rails, refund policy) carries information an agent needs.

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, return-value detail is unnecessary, and the description covers what remains: authoritative source, regulatory basis, scope limits, both query modes, payment/auth requirements and charge policy. An agent can decide whether to call and how to call it without further context.

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 description coverage is 100%, so the baseline is 3; the description still adds value by framing activityId as the second step of a two-call workflow ('from a list result') and by tying NACE/keyword inputs to the returned sector, NACE codes and objectives. It stops short of explaining filter interaction or defaults beyond language.

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 verb and resource — an EU Taxonomy (Regulation 2020/852) activity lookup from the European Commission's Taxonomy Compass API — and enumerates both output modes (eligible activities by NACE code/keyword with sector, NACE codes and objectives; screening criteria for a single activity). It also draws an explicit boundary ('Activity rules only, not company disclosures'), which distinguishes it from disclosure-oriented siblings such as energy_sec_esg_climate_filings.

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 clearly signals the two usage paths — keyword/NACE lookup for lists versus activityId for substantial-contribution and DNSH criteria — and states an exclusion (company disclosures). What's missing is any guidance on picking among the mutually exclusive filters (q vs nace vs objective) or what happens when none is supplied given zero required parameters.

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?

Consistent with readOnlyHint/openWorldHint, and adds context the annotations cannot convey: static vs live data, per-region provenance (US DOE AFDC for US/Canada, OSM elsewhere), and an explicit paid-call model ($0.002 USDC via x402, unsuccessful calls not billed). The cost and billing semantics are exactly the kind of behavior an agent needs before invoking.

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?

Front-loaded with purpose and result shape, then source coverage, then cost — every clause carries information. The heavy parenthetical enumerations make the first sentence dense, but nothing is 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?

With an output schema present and 100% parameter coverage, the description only needs to add scope, data provenance, freshness limits and billing — and it does all four. An agent has everything required to call this correctly and interpret the result.

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 description coverage is 100%, so lat/lon ranges, limit (1-50, default 10) and radius (100-10000 m, default 2000) are already fully documented in the schema. The description adds no parameter-level detail such as units for lat/lon strings or how radius interacts with limit, so 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?

States a specific verb and resource ('EV charging locations near a point') plus the exact return shape (OCPI 2.2 Location → EVSE → Connector with connector standard, power type, max power, operator, hours, status). No sibling tool covers charging infrastructure, so the agent can select it unambiguously.

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?

Clearly signals the use case (proximity search around a coordinate) and the important exclusion that this is static directory data with no live availability. It also says which source applies in which region, which shapes expectations. It stops short of naming an alternative tool for live status, but no such sibling exists.

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?

Goes well beyond the readOnlyHint/openWorldHint annotations: it discloses the pay-per-call model ($0.002 USDC via x402 on Base, Solana or Arc), that failed calls are not charged, and the hard data cutoff date. These are exactly the operational facts an agent needs before spending money on a call.

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?

Three tight sentences: what the data is, the staleness caveat, and the payment terms. Front-loaded with the resource identity and 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?

Trivial input surface (one optional param), an output schema already covers return values, and the description closes the remaining gaps: data currency limit and billing behavior. Nothing an agent needs to call it correctly 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?

Schema description coverage is 100% and the single 'months' parameter (1-24, default 3) is fully documented in the schema. The description only adds the implied ordering ('latest months first') and does not restate the range or default, so baseline 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?

Names the exact resource (FAO Food Price Index monthly values, base 2002-2004=100) and enumerates the returned series (overall plus meat, dairy, cereals, oils, sugar). An agent knows precisely what dataset this returns and the ordering (latest months first). No sibling in the list covers food price indices, so differentiation is implicit but 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?

Gives clear usage context by warning that the published file ends in March 2018, which prevents an agent from misusing it as a current-price source. It does not, however, state an explicit alternative or a when-not-to-use rule beyond that staleness caveat.

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?

The annotations already establish read-only and open-world behavior, and the description adds substantive context beyond them: the data source (World Bank / Solargis), a clear limitation ('not a yield guarantee'), and precise payment semantics ($0.002 USDC per successful call via x402, with failed calls not charged). It does not mention rate limits or latency, but covers the key behavioral traits an agent needs before calling.

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 three dense sentences with no filler: it front-loads what data is returned, then adds the important caveat, then the payment model. Every sentence contributes actionable information for an agent deciding whether and how to call 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 the low complexity (two fully documented parameters), existing output schema, and annotations covering safety, the description is nearly complete: it covers data source, returned variables, usage caveat, and payment details. The main omission is explicit sibling differentiation, which could matter for selecting between this and energy_pvwatts_solar_simulator.

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%, with both lat and lon fully described including ranges and examples, so the structured fields carry the parameter documentation burden. The description adds only that the call is for 'one latitude and longitude,' implying a single-point lookup rather than batch input, which is a marginal addition.

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 (Global Solar Atlas long-term average solar data) at a specific spatial unit (one latitude/longitude) and enumerates the returned fields: PV output, GHI, DNI, diffuse irradiation, and air temperature. It clearly distinguishes itself from general energy tools, but does not explicitly name or differentiate from the closest siblings, energy_pvwatts_solar_simulator and energy_global_wind_atlas_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 use for long-term solar resource screening and includes a caveat that it is 'not a yield guarantee for a specific plant,' which hints at when not to rely on it for bankable yield estimates. However, it never explicitly says when to use it versus alternatives such as energy_pvwatts_solar_simulator, which offers a more detailed PV simulation.

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?

Well beyond the readOnlyHint/openWorldHint annotations, it discloses the pricing model ($0.002 USDC per successful call), the payment rails (x402 on Base, Solana, Arc), and the crucial billing rule that failed calls are not charged. It also discloses methodological assumptions (Rayleigh distribution, air density 1.225 kg/m³) and accuracy limits, which materially affect how the result should be trusted.

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?

One dense paragraph that front-loads the resource and output list before provenance, caveats, and price. Every clause carries information, though the long parenthetical stacks (provenance, method assumptions, pricing) could be split for faster scanning.

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, return values need no explanation; what remains — data source, grid resolution, extrapolation method, accuracy caveat, and cost — is all covered. An agent can decide whether to call this and predict the charge without consulting anything else.

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 description coverage is 100%, with each of lat, lon and hubHeight already documented including ranges and the default. The description adds only indirect context — that hubHeight drives the shear-exponent extrapolation and the resulting 50 m reference — which is marginal beyond what the schema states. Baseline 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?

A specific verb-and-resource statement: wind resource at a coordinate, with the exact returned quantities (10 m and 50 m mean speeds, direction, shear exponent, hub-height extrapolation, power density). It also names the data source (NASA POWER / MERRA-2, ~0.5° grid), which distinguishes it from the sibling energy_global_solar_atlas_pv and from the GWA layers it explicitly rules 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 phrase 'coarse screening data' plus the note that Global Wind Atlas 250 m layers have no public point API tells the agent when this tool is appropriate and why the obvious alternative is unavailable. It stops short of stating exclusions directly (e.g., 'not for bankable energy yield assessment' or 'use the solar atlas for PV'), leaving some inference to the agent.

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 readOnlyHint and openWorldHint annotations, the description discloses pricing ($0.002 USDC per successful call), payment rails (x402 on Base, Solana, or Arc), and that failed calls are not charged. That is meaningful behavioral context for a paid data lookup, though it does not cover rate limits or authentication beyond payment.

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 tool's purpose, then efficiently packs the two view definitions, search behavior, and payment terms into a compact paragraph. Every sentence carries useful information, and there is 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?

Given an output schema and full parameter-schema coverage, the description is largely complete: it covers purpose, view modes, search, and payment. Minor gaps remain, such as whether free-text search applies equally to credit batches and projects, but they do not prevent correct invocation.

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%, so the schema already documents page, view, limit, and query. The description adds real semantic value by enumerating the returned fields for view=credits versus view=projects and by clarifying that the query is a free-text search over names.

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 and resource: 'Gold Standard carbon registry search.' It then spells out the two view modes and the exact fields each returns, which clearly distinguishes this registry-specific tool from sibling registry tools such as Verra VCS, ACR, or CAR.

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 explains how to choose between view=credits and view=projects by listing what each returns, and clarifies that query is a free-text search over names. It does not explicitly say when to use this tool over sibling carbon-registry tools, but the registry-specific scope makes the context clear.

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 only declare readOnlyHint and openWorldHint; the description adds real value beyond them by disclosing the external dependency (live EPEX DE-LU spot substitution) and the commercial terms — $0.002 USDC per successful call via x402 on Base/Solana/Arc, with failed calls not charged. That payment/auth detail is exactly the kind of behavior an agent needs before invoking. It doesn't cover latency, rate limits, or precision of the returned number.

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?

Front-loaded with the core definition, then the default/fallback mechanics, then pricing terms — a sensible order. Three dense sentences with only modest duplication of the defaults that appear again in the schema; nothing is padded or vague.

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 7 optional parameters with full schema coverage, an output schema, and read-only/open-world annotations, the description covers everything an agent needs: what is computed, what units, what defaults apply, where the one external input comes from, and what it costs. No material gap remains.

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 description coverage is 100%, so the baseline is 3. The description restates the same default values the schema already documents (55 kWh/kg, 1000 €/kW, 8% WACC, 20 years, 4000 hours, 3% O&M), adding only the fallback behavior for electricityPrice, which the schema also states. Little semantic value beyond the structured fields.

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?

States a specific verb+resource+unit: levelized production cost (LCOH) of green hydrogen per kg from an electrolyser, with the cost components enumerated (capex annuity, fixed O&M, electricity, water). The closing line 'A transparent calculator, not a traded hydrogen price' explicitly separates it from the spot/price-feed siblings in the energy_* family.

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?

Clear context for invocation: works 'from your inputs or defaults', and the all-important conditional is spelled out — omit the electricity price and the latest EPEX DE-LU day-ahead baseload is substituted. It gives no explicit name-based routing to alternatives (e.g. energy_epex_spot_power_europe for the raw price, energy_ammonia_fertilizer_spot for a traded benchmark), so it stops just short of full when/when-not 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 only declare readOnlyHint and openWorldHint; the description adds substantial context beyond that: a per-call price of $0.002 in USDC via x402, accepted chains (Base, Solana, Arc), and the crucial fact that failed calls are not charged. It also discloses the data range (latest value plus up to 24 months). This is exactly the extra behavioral detail annotations cannot carry.

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?

Purpose is front-loaded and each sentence carries information (source, disambiguation, range, cost). The payment detail is correctly placed last, though the disambiguation clause could be folded tighter to avoid slight redundancy with the name.

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 single-parameter read with an output schema and covered annotations, the description is nearly complete: source, units, history window, cost, and a name caveat are all present. The only missing piece is explicit routing versus sibling agri-price tools.

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%, so the single 'months' parameter and its 1–24 range/default are already fully documented. The description only echoes 'up to 24 months of history', adding marginal confirmation rather than new meaning, so the baseline 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?

Names the specific resource (coffee, sugar, cocoa), the exact nature of the data (monthly world reference prices from FRED / World Bank, USD), and explicitly disambiguates the misleading 'ice' name by stating these are not ICE futures settlements. An agent can tell this apart from related agri tools without opening the schema.

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 gives a clear negative: 'not ICE futures settlements', which steers the agent away from a wrong expectation. However, it never names or contrasts the obvious alternatives in the sibling list (energy_cme_agri_spot_futures, energy_fao_food_price_index), so the positive when-to-use condition is left to inference.

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?

Adds context beyond the readOnly/openWorld annotations: price per successful call, payment rails, the fact that failed calls are free, and that results are the latest year(s) in the source. It does not cover rate limits, auth flow details, or data staleness.

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?

A tight paragraph with the resource, default, caveat, and pricing front-loaded. No wasted sentences, though the payment clause sits mid-paragraph rather than trailing.

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?

Covers defaults, source limitations, and the paid-call model; an output schema exists so return-shape explanation is unnecessary. Missing only explicit sibling routing and error behavior, which are minor for a read-only stats 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?

Schema coverage is 100%, so the baseline is 3. The description adds meaning for the default indicator (CO2 emissions by fuel and product, MtCO2) and echoes the latest-years behavior, but doesn't add syntax or constraints 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?

States a specific verb and resource: IEA energy statistics for one country and one indicator, with the default indicator spelled out. It distinguishes itself from other energy data siblings by naming the source (IEA stats API), but doesn't explicitly route against them.

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 one-country/one-indicator scope and the 'not every indicator has data for every country' caveat imply when the tool applies. There is no explicit when-to-use or when-to-prefer-a-sibling guidance, even though roughly 50 energy siblings exist.

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 and openWorldHint=true. The description adds crucial behavioral context beyond annotations: the cost model ($0.002 per successful call via x402 on Base/Solana/Arc) and that failed calls are not charged. It does not discuss data freshness or rate limits, but the pricing detail is significant.

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?

Three sentences with clear front-loading: purpose first, scope second, pricing third. No wasted words; each sentence adds distinct 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?

With an output schema present and annotations covering safety, the description needs only to convey purpose, scope, and key behavioral traits. It does so well, though it could mention data update frequency or temporal coverage. Overall complete for a filtered data retrieval 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?

Schema description coverage is 100%, so the schema fully documents both parameters (limit and country). The description adds no parameter-specific guidance 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?

States a specific verb+resource: 'IDB project procurement contract awards from the IDB open-data datastore', enumerates returned fields, and clarifies 'Awards only; open tender notices are not in this source', differentiating from notice-oriented siblings like energy_adb_procurement_notices.

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 a clear usage boundary: awards only, no open tender notices. However, it does not name alternative tools for those notices or for other development bank procurement data (e.g., energy_world_bank_procurement), leaving the agent to infer alternatives.

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 and openWorldHint, and the description adds genuinely useful non-schema context: the $0.002 USDC x402 payment model (Base, Solana, Arc) with failed calls not charged, plus the LCOE exclusion. It does not disclose update cadence, pagination, or rate limits, so it is solid but not rich.

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?

Purpose and units are front-loaded, followed by the LCOE exclusion and pricing in two additional compact clauses. The long parenthetical technology list is informative but slightly heavy for a single sentence.

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, return values need no explanation, and the description covers scope (single country), units, technology coverage, and explicit exclusions. Data freshness/update lag and whether years are annual are the only notable 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?

Schema coverage is 100%, so the baseline is 3. The description adds meaning by enumerating the technology categories (solar PV, onshore/offshore wind, hydropower, bioenergy, geothermal) and framing years as 'recent years', giving the agent a better mental model of the filters than the schema alone.

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?

States a specific verb+resource (IRENA renewable energy statistics: installed capacity in MW and generation in GWh) scoped to one country, and enumerates the technology breakdown. It also explicitly excludes LCOE, which separates it from cost-benchmark siblings like energy_nrel_atb_cost_benchmarks or energy_iea_energy_statistics_api.

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?

'for one country' and 'from IRENA's public IRENASTAT database' give a clear usage context, and the LCOE exclusion implicitly routes cost queries elsewhere. However, no sibling is named and there is no explicit when-to-use/when-not statement against comparable statistics tools.

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 establish read-only and open-world behavior, while the description adds meaningful operational context: the exact data source, the fact that the route name is retained for the owner, and x402 payment terms including charges only for successful calls. It does not describe return formatting, but an output schema exists, so the added behavioral value is solid.

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 then adds the benchmark caveat, history scope, and payment terms. Every part is relevant, though the owner-route-name note is slightly less essential than the rest.

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 one-parameter read-only reference-price tool, the description supplies source, frequency, unit, historical range, benchmark caveat, and payment model. With annotations and an output schema also present, an agent has enough context to call 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?

Schema description coverage is 100%, and the single months parameter is already documented as 1 to 24 with default 3. The description's mention of latest value plus up to 24 months of history reinforces but does not materially extend the schema semantics.

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 the specific resource, frequency, unit, currency, and source series: monthly iron ore reference price in USD per dry metric ton from World Bank PIORECRUSDM via FRED. It also explicitly distinguishes this from the Platts 62% Fe CFR Qingdao spot benchmark, so an agent can tell what data it actually returns.

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 clarifies that this is a World Bank monthly reference series rather than the Platts spot benchmark, which is useful selection guidance. However, it does not explicitly state when an agent should choose this tool over related commodity or steel tools, so the usage guidance is strong but not fully 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?

Goes well beyond the readOnlyHint/openWorldHint annotations: it names the upstream source (FRED, World Bank), the currency (USD), the cadence (monthly), the history ceiling (24 months), and the billing model ($0.002 USDC per successful call via x402 on Base, Solana or Arc, failures not charged). The payment disclosure is exactly the kind of behavioral fact an agent must know before invoking.

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?

Four short sentences, front-loaded with what the data is, followed by the naming caveat, the coverage window, and the price. Every sentence carries information an agent needs; nothing is padded.

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?

Return values are covered by the output schema and the billing/source context is thorough. The one residual gap is the schema's odd string typing for months, which the description does not flag, leaving a minor risk of a wrong argument type.

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 description coverage is 100%, so the months parameter (1–24, default 3) is already documented. The description only corroborates it with 'Latest value plus up to 24 months of history', adding the small nuance that the latest point is always returned regardless of window; that is marginal value over the schema, so baseline 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?

States a specific verb and resource: monthly copper, aluminium and zinc reference prices from FRED/World Bank in USD. It also explicitly distinguishes itself from LME cash-settlement pricing and from the route name, so an agent can tell it apart from siblings such as energy_nickel_class1_cash_settle or energy_precious_metals_spot_fix.

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?

Clear usage context: World Bank reference series rather than LME settlement, monthly frequency, latest value plus up to 24 months of history. It does not name a specific alternative for LME-style settlement data or state exclusions, so it stops short of explicit when/when-not routing.

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

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

Annotations already declare readOnlyHint and openWorldHint, so safety is covered. The description adds behavior the annotations cannot: paid access at $0.002 USDC per successful call via x402 on Base, Solana or Arc, and that failed calls are not charged — critical for an agent deciding whether to invoke. It does not discuss rate limits or data freshness lag, which keeps it short of a 5.

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?

A single dense sentence front-loads the data delivered, then the granularity, then price. Every clause carries information. Slightly long for one sentence and a bulleted split of data vs. billing would read better, but there is 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?

An output schema exists, so return-value detail is not required here. The description covers all three data domains (fuel mix, load, forecast), the time granularity, and the cost model — enough for an agent to decide and call. Missing only freshness/cadence expectations for the forecast.

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 takes zero parameters, so the baseline is 4. The description correctly implies a single no-argument snapshot call rather than hinting at filters that do not exist.

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?

States concretely what the tool returns: MISO real-time generation fuel mix by source, total MW, 5-minute interval, system load, hourly cleared load and medium-term hourly load forecast. The name plus 'MISO (Midcontinent Independent System Operator, 15 US states and Manitoba)' makes the coverage area unambiguous. It does not explicitly contrast itself with the similarly-named ISO siblings (CAISO, ERCOT, NYISO), so sibling differentiation is left to inference.

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 statement of when to use this versus energy_caiso_california_iso or energy_ercot_texas_grid_status; the regional scope implicitly selects it. No prerequisites or exclusions are stated. Adequate but the routing is left to the agent.

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?

Goes well beyond the readOnly/openWorld annotations by disclosing the commercial model: $0.002 USDC per successful call via x402 across Base, Solana or Arc, with failed calls not charged. That cost/authorization context is exactly the kind of information an agent needs before invoking a paid tool.

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?

Four compact clauses, front-loaded with what the data is and its units, followed by scope limits and pricing. No filler sentences; each clause adds a distinct fact.

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?

An output schema and annotations already exist, so the description needn't explain return structure. It still covers source provenance, units, coverage limits, and payment terms, leaving nothing material an agent needs before calling.

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% and the single 'days' parameter already documents range and default, so the schema carries the load. The description's 'up to 60 trading days' adds mild clarification of the trading-day semantics but is largely redundant with 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?

States a specific resource (Henry Hub natural gas spot price) with units (USD per MMBtu), source (FRED/EIA series), and returned scope (latest value plus up to 60 trading days). This clearly separates it from siblings such as energy_ttf_european_gas or energy_crude_oil_brent_wti.

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?

Explicitly states what the source does not cover ('Pipeline storage and LNG netback are not included'), which steers an agent away from misuse. It does not, however, name an alternative tool for those adjacent data needs, so routing is only partially handled.

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?

Goes well beyond readOnlyHint/openWorldHint by disclosing the upstream source and series ID, the returned history depth, and a concrete payment model ($0.002 USDC per successful call via x402 on Base/Solana/Arc, failures not charged). Return shape is left to the output schema, which is acceptable here.

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?

Front-loaded with the price definition, then exclusions, then payload/pricing facts; each sentence carries information. The clause about the route name being kept for the owner is marginally useful context rather than noise.

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 single-optional-parameter read tool with annotations and an output schema, the description supplies source, units, history depth, cost, and disambiguation – everything an agent needs to 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?

Schema coverage is 100% and already documents 'months' with range and default. The description adds only a light clarification ('Latest value plus up to 24 months of history'), so the baseline 3 applies – it does not explain units of history or how the latest value relates to the months count.

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?

States a specific verb/resource and scope: 'Monthly nickel reference price in USD per metric ton (World Bank series PNICKUSDM, via FRED)'. It also pre-empts the most likely confusion by naming the sibling product (LME Class 1 cash settlement / warehouse stocks) that this is NOT.

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?

Explicitly excludes the LME cash-settlement interpretation, which routes the agent to energy_lme_metal_cash_settled for that need. There is no positive 'use this when...' statement, but the exclusion plus source naming gives strong selection 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 declare readOnly and openWorld, but the description adds genuinely useful behavior: the data refreshes monthly, and each successful call costs $0.002 via x402 on Base, Solana or Arc with failed calls uncharged — payment/auth context the annotations cannot convey. The classification thresholds (+0.5 / -0.5 / neutral) also tell the agent how values are derived.

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?

Three sentences, front-loaded with the core definition, then thresholds/freshness, then pricing. No filler; the parenthetical threshold explanation is compact and earns its place. Slightly dense but not padded.

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, return-shape detail is unnecessary, and the description covers definition, classification rule, freshness cadence and payment mechanics. Nothing an agent needs to call it correctly is missing, though a hint about typical use (e.g., agricultural/energy demand forecasting) would round it out.

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% and the single 'seasons' parameter is fully documented in the schema with its range and default. The description adds nothing about the parameter, so the baseline 3 applies rather than anything higher.

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 the exact dataset (NOAA CPC Oceanic Nino Index), the measurement (3-month running SST anomaly in Nino 3.4) and the derived label logic, which clearly separates it from every sibling tool in the list. It lacks an explicit action verb ('retrieve/fetch'), so the operation is inferred rather than stated, keeping it just below the top mark.

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?

Usage is implied by the domain — an agent would call this when it needs ENSO state — but the description never says when to use it versus alternatives, nor any exclusions or prerequisites. The only implicit guidance is the 'updated monthly' note, which hints the data is not real-time.

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 only declare readOnly and openWorld; the description adds the material facts an agent needs before invoking: the data source (Nord Pool public portal), the price ($0.002 USDC per successful call), the payment protocol and rails (x402 on Base, Solana or Arc), and that failed calls are not charged. That is exactly the auth/cost context annotations cannot express.

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?

Three sentences, front-loaded with what/where/when, followed by an explicit exclusion and then billing terms. Every clause carries non-redundant information; nothing repeats the schema 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?

With an output schema present the description need not explain return structure, and it covers market scope, units, resolution, source and cost. The remaining gap is small but real: it does not say how far back historical dates are supported or how stale/real-time the published prices are, which matters for a date-parameterized time-series 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?

Schema coverage is 100% and both parameters already document their formats (area codes, YYYY-MM-DD) and defaults (SE3, tomorrow CET), so the schema carries the parameter burden. The description adds only the constraint of one area plus one date per call, not new syntax or semantics.

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?

States a specific verb (retrieves day-ahead Elspot prices) with a precisely bounded resource: one Nordic/Baltic bidding area, one delivery date, EUR/MWh, 15-minute resolution, from the Nord Pool public portal. It also names what it is not (intraday, futures), which separates it cleanly from the EPEX and ENTSO-E power siblings.

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 scope limits give clear usage context: Nordic or Baltic bidding areas only, day-ahead market only, one area and one date per call. It never names a specific alternative sibling (e.g. energy_epex_spot_power_europe for continental Europe), so an agent must infer the routing rule rather than being told it explicitly.

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?

Adds substantive behavioral details beyond the read-only and open-world annotations: it states the latest OEDI release is selected automatically, values are US-focused real dollars as published by NREL, and it specifies the pay-per-success model with x402 on Base, Solana or Arc. The explicit note that failed calls are not charged is important operational context for an agent.

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 three tight sentences with the data source and purpose front-loaded, followed by geographic/value scope and then payment behavior. Every sentence adds useful information for an agent deciding whether and how to call 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 that an output schema exists, the description does not need to explain return formatting. It covers the source, vintage-selection behavior, metric scope, time horizon, geographic/value basis, parameter dimensions, and payment terms, leaving little ambiguity for 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?

Schema description coverage is 100%, so all eight parameters are already documented in the input schema. The description reinforces the metric and scenario dimensions and adds the 2050-2060 horizon, but does not add meaningfully more parameter-level guidance than 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?

States that the tool returns NREL ATB electricity cost projections from the OEDI data lake, naming specific metrics (LCOE, CAPEX, O&M, capacity factor) and dimensions (technology, resource class, year, scenario). The NREL ATB and US-focused framing clearly distinguish it from broader or sibling cost data 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?

The description explains what the data covers but gives no explicit guidance on when to use this tool versus alternatives such as IRENA renewable cost data or EIA statistics. It also includes no exclusions or prerequisites beyond the payment model.

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 cover read-only safety, but the description adds genuinely non-schema behavior: per-call pricing via x402 on Base/Solana/Arc and the fact that failed calls are not charged. It does not describe latency or freshness guarantees beyond 'latest report day', which is a minor gap.

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?

Front-loaded with what data is returned, then scope, then filter, then cost — a sensible ordering with minimal waste. The pricing sentence is dense but earns its place for a paid tool; overall length is slightly long for a single-parameter lookup.

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?

An output schema exists, so return values need no explanation, and the description covers source, scope, filter, and cost. What remains thin is the time dimension (whether 'latest report day' means business days and what happens on weekends/holidays), which matters for a daily report 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?

Schema coverage is 100% and the schema already says 'Optional: part of a unit name, e.g. Vogtle or Diablo'. The description's 'Filter by part of the unit name' restates that substring-match semantics without adding new information, so the baseline 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?

States a specific resource (NRC daily Power Reactor Status Report), specific content (each unit's % of rated power on latest and prior day, plus counts of full-power/reduced/offline units), and explicitly excludes worldwide IAEA PRIS data. That distinguishes it from nearby siblings like energy_uranium_u3o8_yellowcake and energy_us_electric_grid_monitor.

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?

Gives a clear scope boundary ('US units only, about 94; worldwide IAEA PRIS data not included') that tells the agent when this tool will not satisfy a request, and explains the one filter. It does not name an alternative tool for the excluded worldwide case, 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 only cover read-only/open-world safety, but the description adds material behavioral context the annotations cannot: the data source (NYISO MIS files), eastern time stamps, real-time-only market, and critically the cost model ($0.002 USDC per successful call via x402, failed calls not charged). The billing disclosure is exactly the kind of behavior an agent must know before invoking.

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?

A single dense but front-loaded block: purpose first, then data detail, then market scope, then billing. Nearly every clause carries information, though the zone enumeration and component list make it longer than strictly necessary for a one-parameter 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?

With an output schema present, the description needn't document return structure, yet it still explains the price components and the per-zone daily average included. Combined with annotations for safety and explicit billing terms, an agent has everything needed to decide and call 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?

Schema coverage is 100% — the single optional 'zone' parameter already has examples (N.Y.C., LONGIL, CAPITL, WEST). The description echoes the same zone names and adds the useful fact that there are 15 zones/interfaces, but it does not explain what omitting the parameter returns, so it only marginally exceeds 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 names a specific verb+resource (NYISO real-time zonal electricity LBMP prices) and its exact granularity (latest 5-minute values for 15 zones and interfaces), plus the components returned (loss and congestion). It explicitly excludes the day-ahead market, which cleanly separates it from any day-ahead sibling and from the other ISO 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 establishes clear use context: real-time market only, sourced from NYISO public MIS files, eastern timestamps. The exclusion 'day-ahead not included' functions as a when-not signal, though it does not name an alternative tool to use for day-ahead prices.

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 only say readOnly/openWorld; the description adds materially important behavior the agent cannot get elsewhere: a $0.002 USDC charge per successful call via x402 on Base/Solana/Arc, and that failed calls are not charged. Cost and payment-rail disclosure is high-value for an autonomous caller and is not inferable from the schema or 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?

Three tight sentences: identity first, disambiguation second, billing third. No filler, and the awkward 'route name is kept for the owner' note is a one-clause caveat rather than a distraction.

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?

An output schema exists, so return shape needn't be explained. The description still covers source, currency and unit, timestamp semantics, exclusions versus fixings/holdings, and the full payment model — everything needed to call this correctly and know what the caller is paying.

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 description coverage is 100% and the single 'metal' parameter already documents 'XAU (gold) or XAG (silver); default XAU'. The description repeats the same XAU/XAG framing without adding syntax or behavior beyond the schema, so the baseline 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?

States a specific verb+resource with units and source: 'Live spot price of gold (XAU) or silver (XAG) in USD per troy ounce from gold-api.com.' It also pre-emptively distinguishes itself from LBMA London AM/PM fixing and vault holdings, which is exactly the confusion an agent would have with siblings like energy_lme_metal_cash_settled or energy_nickel_class1_cash_settle.

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?

Gives clear positive and negative selection criteria: this is a spot quote with a timestamp, not a fixing and not holdings. That tells the agent when this tool is the right one. It stops short of naming the alternative tool to call when a fixing or holdings data is actually wanted.

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/openWorld annotations it discloses the exact provenance (BLS series via FRED), the history window cap, the pricing model ($0.002 USDC per successful call), the payment rails (x402 on Base/Solana/Arc), and that failed calls are free. That is substantive operational context the annotations 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?

Two sentences, front-loaded with the data identity and the key disambiguation, followed by coverage and payment terms. Even the remark about the route name earns its place by explaining a potentially misleading tool name.

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, return-value detail is rightly omitted. The description supplies provenance, scope, disambiguation, and cost/payment behavior – everything an agent needs to call it correctly and understand the billing consequence.

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% and the month range (1–24, default 3) is already documented in the schema. The description's 'up to 24 months of history' restates that bound rather than adding format or behavioral detail, so baseline 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?

It names the exact BLS series (WPU0911), the source (FRED), the frequency (monthly), and explicitly disambiguates from the RISI NBSK benchmark that the route name implies. An agent can tell precisely what data this returns without opening the schema.

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 exclusion is explicit – 'not the RISI NBSK benchmark' – so an agent seeking the NBSK price knows to look elsewhere. It stops short of naming an alternative tool for that case, but no sibling in the list covers NBSK, so the guidance is effectively complete for this catalogue.

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 only declare readOnlyHint and openWorldHint; the description adds genuinely useful context beyond them — the underlying NSRDB typical-year weather file, an explicit accuracy caveat, and the payment model ($0.002 USDC per successful call via x402 on Base/Solana/Arc, with failed calls not charged). Cost and data-provenance details like this are exactly what annotations cannot express. Rate limits and error behavior are not covered, keeping it from a 5.

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, front-loaded with identity and outputs, then a compact clause for data source, caveat, and price. Every clause carries distinct information and nothing is repeated from the schema 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?

With an output schema present, the description needn't explain return values, and it already lists the key outputs anyway. Annotations cover the read-only posture, the schema fully documents all five parameters, and the description supplies the remaining decision-relevant facts: data source, accuracy caveat, and pay-per-call cost. Nothing an agent needs to decide or call correctly 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?

Schema description coverage is 100% and every parameter (lat, lon, tilt, azimuth, capacityKw) already documents its range and defaults. The description adds only "at a latitude and longitude", which is no more than the required-field statement in the schema. Per the baseline rule, a 3 is correct.

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?

Names a specific upstream model and version (NLR/NREL PVWatts v8) applied to a specific resource and scope (grid-connected PV system at a lat/lon), then enumerates the exact outputs: annual AC energy, capacity factor, annual solar radiation, monthly AC energy. That is far more than a restated name. It never distinguishes itself from the closest sibling, energy_global_solar_atlas_pv, which also deals with site-level solar resource, so it stops short of a 5.

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?

"Grid-connected PV system" and "this is an estimate, not a yield guarantee" implicitly scope the tool to pre-feasibility yield estimation, but there is no explicit when-to-use or when-not language and no routing to the alternative solar tools. An agent must infer the choice from domain knowledge.

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 only cover readOnly/openWorld, and the description layers on material context: the upstream source (RGGI's public auction results table), auction cadence (quarterly), recency ordering, and a per-call billing model ($0.002 USDC via x402 across Base/Solana/Arc with failed calls free). That cost/scope disclosure is exactly what an agent needs before invoking a paid endpoint.

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?

One dense sentence for the payload, then two short sentences for scope and pricing. Purpose is front-loaded; every clause (fields, cadence, ordering, source, exclusions, cost) carries unique 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?

For a read-only, single-parameter tool with an output schema and full annotations, the description covers scope, source, ordering, and payment terms. Nothing an agent needs to call it correctly 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?

Schema description coverage is 100% and the single `limit` parameter already documents its range (1–80) and default (8). The description adds nothing about the parameter, which is acceptable when the schema carries it fully.

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?

States a specific verb+resource (RGGI CO2 allowance auction results) and enumerates exactly the fields returned: auction number/date, quantity offered, CCR sold, quantity sold, clearing price, total proceeds. The 'Quarterly auctions only; secondary-market prices are not included' clause separates it from the spot-price and registry siblings (energy_american_carbon_registry, energy_verra_vcs_registry).

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?

Gives a clear exclusion ('secondary-market prices are not included') and implies the primary-auction use case, plus ordering ('latest first'). It does not name a specific alternative tool for secondary-market pricing, so routing is inferred 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?

Annotations already declare readOnlyHint and openWorldHint, so the safety profile is covered. The description adds meaningful behavioral context beyond annotations: per-call pricing of $0.002 USDC via x402 on Base, Solana or Arc, and the fact that failed calls are not charged.

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 tool's purpose and packs relevant valuation and pricing details into two sentences. It is dense but appropriate for a financial-data endpoint; a minor deduction for the long currency-list clause.

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 takes no parameters and has an output schema, the description is complete enough: it identifies the data source, the valuation date convention, the basket composition, the conversion formulas, and the pricing model. Nothing an agent needs in order to call it correctly 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?

This tool has zero parameters, so the baseline score is 4. There are no parameter semantics to explain, and schema coverage is irrelevant for an empty input object.

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 states a specific resource and scope: IMF Special Drawing Rights valuation for the latest IMF business day, with detailed breakdowns of basket currencies and SDR/USD conversions. It is clearly distinct from the sibling exchange-rate and commodity tools, though it does not explicitly name an alternative for comparison.

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 explains what the tool returns but gives no explicit guidance on when to use it versus alternatives such as energy_bis_effective_exchange_rate or other FX-related siblings. Usage context is only implied by the tool's purpose and the 'latest IMF business day' scope.

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?

Goes well beyond the readOnlyHint/openWorldHint annotations by disclosing the paid-access model — $0.002 USDC per successful call via x402 on Base, Solana or Arc, with failed calls uncharged — plus the shape of the response (total hit count, latest filings with company, CIK, form, file date). Cost and payment mechanics are exactly the sort of behavior an agent must know before invoking.

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?

Front-loads what the tool searches, then the return shape, then the scope caveat, then the price. Four dense sentences, each carrying distinct information, 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 read-only, paid, open-world search tool the description covers invocation intent, output contents, a scope limitation, and payment/failure semantics. With an output schema present, return values needn't be fully specified, so nothing essential 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?

Schema coverage is 100%, so the baseline is 3; the description adds value by giving concrete example phrases ('climate risk', 'scope 1 emissions') that illustrate the intended query granularity and by noting results are the *latest* matches. It doesn't discuss the limit range or character constraints, but those are already in 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?

States a concrete verb and resource — SEC EDGAR full-text search of 10-K (or other) filings whose text contains a phrase — with example queries. This clearly separates it from adjacent tools like energy_epa_flight_emissions or energy_climate_action_registry, which measure emissions rather than search filing text.

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?

Gives a clear use context (find which companies mention a phrase) and an explicit negative boundary: 'it does not extract emission numbers.' It does not name a specific sibling to use instead when actual emissions data is wanted, so it stops short of full alternative routing.

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 cover read-only and open-world behavior, and the description adds real value beyond that: the price ($0.002 USDC per successful call), the payment rail (x402 on Base, Solana or Arc) and the fact that failed calls are not charged. That is exactly the kind of billing context annotations cannot express.

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 tight sentences: identity plus source first, then the disambiguation, then pricing. The clause about the route name being kept for the owner is slightly extraneous but explains why the tool name is misleading.

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?

Source, series ID, frequency, unit type, scope exclusion and cost model are all present, and an output schema exists so return values need no explanation. Minor gaps remain on index base/revision behavior, but nothing blocks correct invocation.

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 optional parameter (months) with 100% schema description coverage including the 1-24 range and default of 3. The description adds nothing about the parameter, but the schema fully carries it, so the baseline 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?

Names the exact resource (US producer price index for steel mill products, BLS series WPU1017 via FRED) and the frequency/units (monthly index value). It explicitly disclaims being hot-rolled coil or rebar futures or spot benchmarks, which is the main confusion risk against siblings like energy_iron_ore_62_percent_fe or energy_thermal_coal_newcastle.

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?

Gives a clear use/not-use split: use it for the steel mill products PPI, not for HRC/rebar futures or spot benchmarks. It doesn't name a specific sibling to use instead for futures pricing, so the routing is only implied, not 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?

Annotations cover the read-only/open-world profile, and the description adds highly consequential context they cannot: the $0.002 USDC per-successful-call cost, the x402 payment rails (Base, Solana, Arc) and that failed calls are not charged. Cost and payment mechanics are precisely what an agent needs before invoking a paid tool.

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 lead sentence carries the identity and units, and the pricing note is placed last where it belongs. The clause 'the route name is kept for the owner' is minor internal noise that does not help an agent decide anything.

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, return values need no prose, and the description still supplies series ID, units, cadence, history depth, cost and payment rails. Nothing needed to call it correctly 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?

Schema coverage is 100%, so the baseline is 3, but the description reinforces the ceiling ('up to 24 months of history') and clarifies the result shape ('latest value plus up to 24 months'), which adds meaning about what the months parameter actually controls.

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 (Australian thermal coal reference price), unit (USD per metric ton), cadence (monthly) and exact source (World Bank PCOALAUUSDM via FRED). It also explicitly disambiguates from the Newcastle FOB spot index and Richards Bay, which is exactly the confusion the route name invites.

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 exclusions ('Not the Newcastle FOB spot index or Richards Bay prices') route the agent away from mismatched expectations, but there is no positive statement of when to pick this over adjacent price series. It is a clear context statement rather than a full when/when-not rule set.

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