osint

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the description is not required to restate safety. The description adds no extra behavioral context (e.g., return format or side effects), but with annotations covering the safety profile, this is acceptable.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

The description is a single sentence that front-loads the verb 'Describe' and immediately lists the object types covered. It contains no filler, redundancy, or unnecessary detail.

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 no-parameter tool with an output schema, the description fully covers the agent's needs: it states the exact resource and what aspects are described. No additional context is necessary.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero input parameters, so parameter semantics are inherently not needed. The description instead clarifies what the output describes, which is appropriate given the 100% schema coverage (empty schema).

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses the specific verb 'Describe' and enumerates the exact categories (filters, groupings, metrics, detail fields, citation fields) for ai_infrastructure.construction, clearly distinguishing it from query_* siblings. It specifies both the resource and the scope of the description.

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 this tool is for discovering valid query parameters for the construction dataset, but it does not explicitly state when to use it versus the companion query_ai_infrastructure_construction_v1. No alternatives or exclusions are mentioned.

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, idempotentHint=true, and destructiveHint=false, so the safety profile is well covered. The description adds no new behavioral traits beyond listing what aspects it describes, which is more about content than behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

The description is a single, front-loaded sentence that conveys all necessary information without redundancy. It is efficiently structured and easy to parse.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool has no parameters, annotations cover safety, and an output schema exists, the description is fully adequate. It clearly scopes the tool to a specific dataset and indicates what kind of information will be provided.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero parameters, so the baseline is 4. The description adds useful context by naming the dataset and the categories of information it describes, even though no parameter-specific semantics are needed.

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 verb 'Describe' and a specific resource 'ai_infrastructure.employment', enumerating exactly what it covers (filters, groupings, metrics, detail fields, citation fields). This clearly distinguishes it from sibling describe tools for other datasets.

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 the tool: when you need to know the valid query options for ai_infrastructure.employment. It doesn't explicitly mention alternatives or exclusions, but the context is clear from the dataset specificity and sibling 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 declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds no extra behavioral context (e.g., auth requirements, rate limits, response format nuances), so it meets the baseline for annotation-supported descriptions but does not exceed it.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

The description is a single, front-loaded sentence that conveys the full purpose without any superfluous words or repetition.

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 no parameters and an output schema, the description sufficiently covers the tool's role by listing the metadata categories it returns. It doesn't need to explain return values because the output schema exists and the categories are clearly stated.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero parameters, so the baseline is 4. The description correctly focuses on output categories; no parameter documentation is needed since the input schema is empty.

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 'Describe' and names the exact resource 'ai_infrastructure.equipment_trade'. It also enumerates the categories of information (filters, groupings, metrics, detail fields, citation fields), making it distinct from sibling describe tools like describe_ai_infrastructure_trade_v1.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description does not explicitly state when to use this tool versus the corresponding query tool or other describe alternatives. It lacks any mention of when-not-to-use, prerequisites, or comparisons to siblings, despite the presence of 'describe' and 'query' pairs in 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, idempotentHint=true, and destructiveHint=false, covering the safety profile. The description adds value by specifying exactly what metadata will be described (filters, groupings, metrics, detail fields, citation fields), giving a clear behavioral contract beyond the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

The description is a single, well-structured sentence that front-loads the verb and resource, listing all the covered aspects without wasted words or redundancy. It is concise and informative.

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 the tool has no input parameters and an output schema is present to explain return values, the description provides sufficient context. It fully enumerates the categories of information the tool returns, making it complete for an agent to decide when and how to use it.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool accepts zero parameters, and the schema description coverage is 100%, so there are no parameter semantics to clarify. The description correctly focuses on what the tool returns rather than parameters, which is appropriate for this describe tool.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses the specific verb 'Describe' and names the exact resource 'ai_infrastructure.production', clearly distinguishing this from sibling describe tools for other datasets. The title adds context about semiconductor output and utilization, further clarifying the tool's focus.

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 this tool is used to discover valid filters, groupings, and metrics for querying the production dataset, but it does not explicitly state when to use it versus alternatives or mention the companion query tool. The intended usage is inferable rather than directly 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 declare readOnlyHint=true and idempotentHint=true, so the read-only nature is covered. The description adds meaningful behavioral context beyond the annotations by listing the specific categories of metadata returned (valid filters, groupings, metrics, detail fields, citation fields), which is exactly what an agent needs to know before querying. No contradictions with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

The description is a single, front-loaded sentence that precisely states what the tool does. No wasted words; every element ('valid filters, groupings, metrics, detail fields, and citation fields') earns its place by specifying the tool's full scope.

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 describe tool with no parameters and an existing output schema, this description is complete. It tells the agent exactly what metadata will be described and explicitly names the target dataset. The presence of an output schema covers the return structure, so no additional explanation is needed.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero parameters and the schema is empty with 100% schema description coverage. The baseline for zero parameters is 4, and the description does not need to add parameter semantics since none exist. It correctly focuses on the output behavior.

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 ('describe') and explicitly names the resource ('ai_infrastructure.trade') and the exact categories of information it returns (filters, groupings, metrics, detail fields, citation fields). This clearly distinguishes it from the many sibling describe tools for other datasets.

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 that this tool is a metadata/describe companion to query_ai_infrastructure_trade_v1, but it does not explicitly state when to use it versus alternatives or provide any 'when not to use' guidance. The purpose is clear from the verb and resource, but the usage context is only implied by the sibling tool names.

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, idempotentHint=true, destructiveHint=false. The description adds meaningful context: it returns the same schema payload as named describe tools, accepts two kinds of identifiers, and works for capabilities shipped after a client's cached tool list. This goes beyond the annotations, though it doesn't cover error cases 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?

The description is efficient and well-structured: a front-loaded purpose statement, followed by parameter guidance, and ending with usage context. Every sentence carries necessary 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?

Though an output schema exists, the description still summarizes the return payload (valid filters, groupings, metrics, detail fields, citation fields). It covers the generic-vs-named tool relationship, parameter choices, and the unique caching scenario, making it complete for the tool's complexity.

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 has only a bare 'capability' string with no description (0% coverage). The description fully compensates by specifying valid values: a capability id from list_capabilities_v1 (e.g., 'power.capacity') or a query primitive name (e.g., 'query_power_capacity_v1'). This is essential semantic information.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: 'Describe any served capability by name' — a specific verb+resource action. It explicitly differentiates itself as 'the generic twin of the named describe tools', distinguishing it from the many sibling describe_* 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?

Provides explicit when-to-use guidance: 'Use the generic pair (this + query_capability_v1) when list_capabilities_v1 names a capability that has no named tool in your client's tool list'. It also explains the parameter format (capability id or query primitive name) and the caching rationale, making usage 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 already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, covering the safety profile. The description adds behavioral context by specifying the metric formula and the data sources (EIA-860M and EIA-923), which is useful beyond the annotations. It does not contradict the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

The description is a single, well-structured sentence that includes the formula and data sources without any wasted words. It is immediately understandable and front-loaded with the core purpose.

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 this is a describe tool with no parameters, an output schema present, and comprehensive annotations, the description is complete. It fully explains what the tool does, which is to describe the capacity factor metric, including its calculation and underlying data sources. No additional context is needed.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has zero parameters, so there is nothing to document. With no parameters, the baseline is 4, and the description does not need to add parameter semantics. The formula and data sources are sufficient.

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 'Describe' and clearly identifies the resource as 'capacity factor', providing the exact formula. This distinguishes it from sibling tools like query_capacity_factor_v1 (which likely queries data) and other describe tools such as describe_power_capacity_v1. The purpose is unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies the tool is used to obtain the definition and calculation of capacity factor, and the formula provides context. However, it does not explicitly state when to use this tool versus alternatives or exclude query usage. The guidance is implied rather than explicit.

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

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

Annotations already cover read-only, idempotent, and non-destructive behavior. The description adds valuable context about the scope of the description (specific dataset and metadata aspects), which goes beyond the annotations. No contradictions found.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

The description is a single, front-loaded sentence that lists all key aspects without any fluff. It is concise and directly conveys the tool's purpose.

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 no parameters and an output schema present, the description is complete for a zero-parameter describe tool. It clearly communicates what the tool covers (dataset and metadata aspects), making it easy for an agent to select it appropriately.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero parameters, so the baseline is 4. The empty schema fully documents the lack of parameters, and the description does not need to add any parameter information.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool describes EIA Henry Hub and state electric-power gas-price atoms, listing specific metadata aspects like units, aggregate grain, missingness, vintages, and citations. This specific verb+resource combination distinguishes it from sibling query tools and other describe 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 implies this is for understanding dataset metadata (units, missingness, vintages) versus querying actual prices, but it does not explicitly state when to use this tool over query_natural_gas_prices_v1 or other describe tools. No alternatives or exclusions are mentioned.

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, idempotentHint, and destructiveHint, so description adds context about what it describes but no extra behavioral traits. Consistent with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

Single sentence that is concise and lists key elements. Could be marginally more structured, but it's efficient and front-loaded.

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 exists, the description adequately covers the tool's purpose. It mentions filters, convention, metrics, and citations, which is sufficient for a describe tool. However, it doesn't explicitly tie to the output 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?

Input schema has zero parameters, so there is no need for parameter explanation. Description could mention it takes no arguments, but schema coverage is 100% and no param info is required.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states what the tool does: it describes annual EIA-860 ownership filters, convention, metrics, and exact-cell citations. It uses a specific verb and resource, distinguishing it from sibling describe tools that cover other topics.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No explicit guidance on when to use this tool versus alternatives (e.g., query_power_asset_ownership_v1). The usage is implied as descriptive, but lacks when-not-to-use or alternative mentions.

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, idempotentHint=true, and destructiveHint=false, so the agent knows this is a safe read operation. The description adds no additional behavioral details beyond listing content areas, which is acceptable given the annotation coverage.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

The description is a single, information-dense sentence that lists key content areas. It is front-loaded with the verb and resource, free of filler, and appropriately sized for its purpose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool has no parameters, an output schema, and annotations, the description adequately specifies what the tool describes (document kinds, resource classes, ratios, suppressions, citations). This is sufficient for an agent to invoke the tool correctly and understand its 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?

The tool has zero parameters, so the schema is fully covered. Per the rubric, a tool with no parameters receives a baseline of 4, and the description does not need to explain parameter syntax. The content list helps the agent understand what will be described.

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 the verb 'Describe' with a specific resource: 'MISO accreditation document kinds, resource classes, ratios, suppressions, and citations.' It explicitly names MISO, distinguishing it from sibling tools like describe_power_capacity_accreditation_pjm_v1 and describe_power_capacity_market_miso_v1.

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 context is clear: the tool should be used when one needs to understand MISO accreditation document kinds, resource classes, ratios, suppressions, and citations. It does not explicitly state exclusions or alternatives, but the domain is well-specified, and the tool name itself differentiates from PJM equivalents.

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, idempotentHint, and destructiveHint=false, so the description need not restate those safety traits. It adds context by indicating that the tool covers ELCC document identities, class dimensions, metrics, and citations, but it does not disclose the return format, pagination, or the 'internal' access implication suggested by the title, leaving behavioral detail largely to the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

The description is a single sentence with no filler, front-loading the action ('Describe') and domain ('PJM ELCC'). Each phrase adds a distinct content category (identities, dimensions, metrics, citations), so every word earns its place.

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, parameterless describe tool, the description is mostly sufficient: it names the domain and the kinds of information described, and an output schema exists to provide structural detail. It does not expand 'ELCC' or explain why 'class dimensions' means, but given the low complexity and the presence of an output schema, the remaining gaps are not severe.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has zero parameters, so there is no parameter-level meaning for the description to clarify; the empty properties object says everything. Per the rubric, a 0-parameter tool gets a baseline of 4 since parameter semantics are not applicable, and the description does not need to compensate.

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 domain (PJM ELCC) and a concrete action ('Describe'), and it lists four content areas: document identities, class dimensions, metrics, and citations. This distinguishes it from sibling describe tools by focusing on ELCC, but the terms like 'class dimensions' and 'document identities' are somewhat jargon-heavy and the title's explicit 'Class Ratings' is not reflected in the description, so it is clear but not maximally crisp.

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 no guidance on when to use this tool versus alternatives. There is no mention of the companion query_power_capacity_accreditation_pjm_v1 or any exclusions such as 'do not use for other PJM capacity datasets', so an agent must rely on the general 'describe' convention and tool name to infer usage.

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, idempotentHint=true, and destructiveHint=false. The description adds no behavioral context beyond that, such as scope limitations, response behavior, or access requirements. No contradiction exists, but no value is added beyond the structured annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

The description is a single, focused sentence that front-loads the core purpose and avoids all filler or redundancy. Every word contributes meaning.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a describe-only tool with no parameters and an output schema, the description adequately communicates the scope (MISO PRA capacity-market fields). However, it lacks any usage guidance or context about how the described fields relate to query counterparts, which slightly reduces completeness.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero parameters, so the schema fully covers all inputs. The baseline of 4 applies; no additional parameter explanation is needed or provided.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's action (describe) and specific resource (MISO PRA capacity-market fields), enumerating field types: planning-year, season, zone, parameter, and citation. This distinguishes it from sibling tools like describe_power_capacity_market_pjm_v1 and describe_power_capacity_accreditation_miso_v1.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives, no exclusions, and no mention of related query tools. It only restates the tool's purpose without contextualizing selection.

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 annotations readOnlyHint=true, idempotentHint=true, and destructiveHint=false, the safety profile is already disclosed. The description adds scope content ('delivery-year/LDA filters, UCAP metrics, and citations') but does not reveal behavioral traits such as whether the tool returns metadata only or requires an active session. No contradiction with annotations exists.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

The description is a single sentence with 10 words, front-loading the core purpose without extraneous detail. Every word adds value, and the structure is highly efficient for an agent scanning tool lists.

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 zero-parameter, non-destructive describe tool with an output schema, the description covers the key subjects (filters, metrics, citations) adequately. However, it does not mention how this tool relates to query_power_capacity_market_pjm_v1 or how the described elements map to query parameters, which would improve completeness. The output schema offloads return-value documentation, so the lack of output detail is acceptable.

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 accepts zero parameters, so the baseline of 4 applies. The description does not need to explain parameter semantics, and the input schema confirms an empty parameter set, making the description sufficient.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly specifies the verb 'Describe' and the resource 'PJM RPM delivery-year/LDA filters, UCAP metrics, and citations,' which distinguishes it from sibling tools like describe_power_capacity_accreditation_pjm_v1. However, it does not explicitly explain what 'describe' outputs (e.g., schema definitions, option lists), leaving some ambiguity about the tool's exact behavior.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives. It does not reference the corresponding query tool 'query_power_capacity_market_pjm_v1' or any conditions for preferring this describe tool over others. This lack of usage context forces the agent to rely on naming conventions 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?

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, covering safety. The description adds specific context about the categories of metadata it returns (filters, groupings, metrics, etc.), which is helpful beyond the annotations. No contradictions found.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

The description is a single, concise sentence that front-loads the action and resource. It contains no unnecessary words and is easy to parse.

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 simplicity of the tool (no parameters, output schema present, read-only annotations), the description is complete. It clearly explains what the tool does and lists the specific categories of information it describes.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero parameters, so baseline is 4 per rubric. The empty input schema is fully covered, and there is no need for parameter descriptions in the tool text.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: to describe valid filters, groupings, metrics, detail fields, and citation fields for the specific resource 'power.capacity'. It uses a specific verb and resource, distinguishing it from sibling describe_* tools that target other datasets.

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: the agent can infer that this tool is useful when needing to know the queryable fields for power.capacity. However, there is no explicit guidance on when to use it versus alternatives, such as query_power_capacity_v1, or any 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 declare the tool as read-only, idempotent, and non-destructive. The description adds value by specifying the categories of information returned (filters, groupings, metrics, etc.), which clarifies the tool's output nature beyond the generic 'describe' label. There is no contradiction with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

The description is a single concise sentence that front-loads the verb and enumerates the metadata categories. Every word contributes to understanding the tool's purpose, with no redundant or extraneous content.

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 deterministic metadata-retrieval nature, the presence of an output schema, and comprehensive annotations, the description fully communicates the tool's role. It does not need to explain return formats since the output schema covers that. The description is complete for an agent to select and invoke the tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero parameters, so the input schema provides no parameter details. Per the rubric, baseline is 4. The description does not add parameter-specific information, but that is unnecessary given the absence of parameters.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's function: to describe valid filters, groupings, metrics, detail fields, and citation fields for the resource power.demand_rollup. It uses a specific verb ('describe') and identifies the exact resource, distinguishing it from sibling tools like describe_power_demand_v1.

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 conveys that the tool provides metadata about the rollup endpoint, which implicitly indicates when to use it (e.g., before querying power.demand_rollup). However, it does not explicitly state usage conditions or contrast with alternative tools, leaving the guidance somewhat implied rather than direct.

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 idempotentHint=true, so the safety profile is clear. The description adds valuable context beyond annotations by specifying the categories of metadata returned (filters, groupings, metrics, detail fields, citation fields), which helps the agent know what to expect without contradicting the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

The description is a single, front-loaded sentence of about 15 words. Every word is meaningful—it identifies the action, the dataset, and the scope. No filler or redundant phrasing.

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 zero-parameter describe tool with an output schema present, the description fully captures what the tool does and what it returns at a high level. It leaves no ambiguity about the dataset or the categories of information described, making it complete for its simple 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?

The tool has zero parameters, so the baseline is 4. The description correctly focuses on the describe functionality rather than any parameter details, and no additional parameter semantics are needed.

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 verb ('Describe') and a specific resource ('power.demand'), and enumerates the exact aspects covered (valid filters, groupings, metrics, detail fields, and citation fields). The tool name further distinguishes it from sibling describe tools for other datasets, making purpose unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies its usage context—an agent would use this tool to learn the valid query components for power.demand. However, it does not explicitly state when to use this over query_power_demand_v1 or other describe tools, nor does it provide exclusions or alternative 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 declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds behavioral context by mentioning 'exact-cell citations' and 'missing semantics,' which informs the agent about the tool's output structure beyond the annotations. No contradictions.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

The description is a single, well-structured sentence that front-loads the core purpose ('Describe EIA-923 receipt/cost filters') and lists specific aspects covered. It contains no extraneous words or redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given zero parameters, complete annotations, and an existing output schema, the description adequately covers what the tool does. It specifies key details like exact-cell citations and missing semantics, ensuring the agent understands the return format without needing further explanation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero parameters, so the baseline score is 4. The description does not need to add parameter-level meaning, and it appropriately describes the tool's function without referencing nonexistent parameters.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool describes 'EIA-923 receipt/cost filters, raw units, missing semantics, and exact-cell citations.' It uses a specific verb ('describe') and resource domain ('power fuel cost'), distinguishing it from sibling describe tools focused on other domains (e.g., describe_capacity_factor_v1).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for obtaining metadata about EIA-923 receipt/cost data, but it does not explicitly state when to use this tool versus alternatives like query_power_fuel_cost_v1 or other describe tools. No when-not or exclusion guidance is provided.

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

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

Annotations already declare the tool as read-only, idempotent, and non-destructive. The description adds context by enumerating the types of metadata returned (filters, groupings, atoms, metrics, detail fields, citation fields), which goes beyond the annotations and helps the agent understand what to expect.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

The description is a single, front-loaded sentence that lists the key types of information without any unnecessary words. It is highly concise and well-structured.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity (no parameters, no nested objects, output schema present), the description fully covers the tool's purpose and scope. It clearly specifies what is described (valid filters, etc.) and is complete for a describe 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?

The tool has zero parameters, so the schema provides full coverage trivially. The description does not need to explain parameters, and the baseline for zero-parameter tools is 4. It appropriately focuses on the tool's output content.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool 'Describe valid filters, groupings, atoms, metrics, detail fields, and citation fields for power.generation.' This specifies a concrete action (describe) and distinct resource (power.generation metadata), differentiating it from query_power_generation_v1 and other describe 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 implies this tool is used to obtain metadata before constructing queries, but it does not explicitly state when to use it vs. alternatives like query_power_generation_v1 or other describe tools. No exclusions or alternative guidance is provided.

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, idempotentHint=true, and destructiveHint=false, so the safety profile is clear. The description adds context by enumerating the categories of information it describes (filters, groupings, metrics, etc.), but does not disclose additional behavioral traits such as return size or performance characteristics.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

The description is a single sentence that front-loads the verb and clearly lists the output categories. It contains no filler or redundant 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?

Given the tool has no parameters, an output schema is present, and annotations cover safety, the description is complete for selecting and invoking this tool. It tells you what information it provides, which is all that is needed.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has zero parameters, so there are no parameter semantics to explain. The baseline score for 0-param tools is 4, and the description appropriately does not over-explain anything.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's function: to describe valid filters, groupings, metrics, detail fields, and citation fields for the power.interconnection_queue_caiso dataset. It uses a specific verb ('Describe'), names the exact resource, and is distinguished from siblings like describe_power_interconnection_queue_ercot_v1 by the caiso suffix.

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 the tool is used to learn about query parameters for the CAISO interconnection queue dataset, but it does not explicitly state when to use it versus alternatives, such as the corresponding query tool or other regional describe tools. No exclusions or explicit 'when to use' guidance is provided.

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

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

Annotations already declare the tool read-only, idempotent, and non-destructive. The description adds context about the content of the description (valid filters, groupings, etc.), which is useful and goes beyond the annotations, though it does not disclose additional behavioral traits like return structure or limitations. With annotations present, this is adequate.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

The description is a single, front-loaded sentence that avoids redundancy. Every word contributes to conveying the tool's scope, making it concise and well-structured.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool is simple with no parameters, and an output schema exists to explain return values. The description covers all necessary aspects to understand the tool's purpose and fits well within the context of sibling describe 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?

The tool has zero parameters, so there are no parameter semantics to explain. The baseline of 4 applies, and the description does not need to compensate for any missing parameter information.

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 the specific verb 'Describe' and names the exact resource 'power.interconnection_queue_ercot', listing the types of information covered (filters, groupings, metrics, detail fields, citation fields). This clearly distinguishes it from sibling tools for other datasets.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description does not explicitly state when to use this tool versus alternatives. It implies usage through its name and scope, but there is no guidance on when to choose the ERCOT-specific tool over the generic describe_power_interconnection_queue_v1. Thus usage is only implied.

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 mark this as read-only, idempotent, and non-destructive. The description adds specific behavioral context by enumerating the categories of information (filters, groupings, metrics, detail fields, citation fields) that the tool returns, which is not captured in the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

The description is a single, front-loaded sentence that clearly states the tool's output scope with no filler or repetition. Every word earns its place.

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 tool has no parameters and provides an output schema. The description sufficiently covers the tool's purpose and the categories of metadata it returns, making it complete for its simple nature.

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 accepts zero parameters, so the schema fully covers parameters. Per the rubric, the baseline for zero parameters is 4, and no additional parameter semantics are needed since there are none.

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 the specific verb 'Describe' and identifies the exact resource: valid filters, groupings, metrics, detail fields, and citation fields for the ISO-NE interconnection queue dataset. This clearly distinguishes it from sibling describe tools for other regions or datasets.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no explicit guidance on when to use this tool versus alternatives, such as using it before querying the corresponding data. Usage is implied by the tool's purpose, but no prerequisites or alternatives are mentioned.

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, idempotentHint=true, and destructiveHint=false, so the tool is safely read-only. The description adds context by specifying the exact categories of information returned (filters, groupings, metrics, etc.), which is valuable beyond the annotations. No contradictions.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

A single sentence, front-loaded with the verb and resource, enumerates the key content types. Every word earns its place; no waste or redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple describe tool with no parameters and an output schema (implied by has output schema), the description is complete. It tells the agent exactly what this tool provides, and the read-only nature is covered by annotations. No gaps in 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?

The tool has zero parameters, so schema coverage is trivially 100%. The description doesn't need to explain parameters, and the baseline for 0 params is 4. The description adds no unnecessary parameter details.

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 ('Describe') and resource ('power.interconnection_queue_nyiso'), clearly indicating this tool provides metadata about the NYISO dataset. It distinguishes itself from sibling describe tools for other regions (e.g., caiso, ercot) by naming the exact dataset, and from query tools by its descriptive role.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage: it lists what the tool describes (valid filters, groupings, metrics, detail fields, citation fields), making it clear this is a reference for constructing queries to the NYISO interconnection queue. It does not explicitly exclude other tools, but the dataset-specific naming provides clear context among siblings.

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, idempotentHint=true, and destructiveHint=false, covering the safety profile. The description adds context about the specific output aspects (filters, groupings, metrics, detail fields, citation fields) but does not disclose any additional behavioral traits beyond what annotations and the tool name imply. This is adequate but not exceptional.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

The description is a single, focused sentence that is front-loaded with the verb 'Describe' and immediately identifies the resource and the specific aspects covered. Every word earns its place; there is no redundancy or extraneous content.

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 simplicity (0 params, output schema present, annotations provided), the description is complete for its purpose. It clearly states what the tool describes and for which dataset. The resource name includes 'cycle', aligning with the title, and the output schema covers return values, so no further explanation is needed.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero parameters, so the input schema is already fully covered (100%). The description does not need to elaborate on parameters. The baseline for 0 params is 4, and the description adds no unnecessary parameter information, which is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's function: to describe valid filters, groupings, metrics, detail fields, and citation fields for a specific dataset. The resource 'power.interconnection_queue_pjm_cycle' is precisely identified, and the verb 'describe' distinguishes it from query tools. The explicit list of what is described adds specificity and differentiates it from other describe 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 implies a clear usage context: when an agent needs to know the valid filters, groupings, metrics, detail fields, or citation fields for this dataset, use this tool. It does not explicitly name alternatives, but the distinction between describe and query tools and the dataset-specific naming provide sufficient context. No exclusions are given, but the purpose is 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 already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, covering safety and idempotency. The description adds value by detailing the types of information returned (filters, groupings, metrics, detail fields, citation fields), which clarifies the tool's output scope. No contradiction with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

The description is a single, front-loaded sentence that efficiently lists the categories of metadata the tool provides. No wasted words; every element is informative.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool has no parameters and an output schema exists, the description sufficiently covers what the tool does. It names the key aspects (filters, groupings, metrics, detail fields, citation fields), which is complete for a describe tool. Slight gap: it doesn't explicitly connect to the corresponding query tool, but this is not essential.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero parameters, so schema coverage is effectively 100%. The description doesn't need to explain parameters since none exist. It appropriately focuses on what the tool returns rather than input 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 clearly states the tool's purpose: to describe valid filters, groupings, metrics, detail fields, and citation fields for a specific resource (power.interconnection_queue_pjm). The verb 'describe' is specific, and the resource is uniquely identified, distinguishing it from query tools and describing what metadata aspects are covered.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no explicit guidance on when to use this tool versus alternatives. While the name implies it is for PJM data, there is a generic describe_power_interconnection_queue_v1 sibling that could be used instead, and the description does not explain when to choose this region-specific version. No exclusions or context are given.

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, idempotentHint=true, destructiveHint=false, providing a safe-read profile. The description adds context by specifying exactly what categories of metadata will be returned (filters, groupings, metrics, detail fields, citation fields), which goes beyond the annotations without contradicting them.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

The description is a single, front-loaded sentence that wastes no words. It clearly begins with the verb and resource, then lists the content categories. No unnecessary detail or repetition.

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 this is a describe tool with an output schema and strong annotations, the description is sufficiently complete. It names the dataset and enumerates the fields it documents, which is all an agent needs to decide whether to call it. However, it does not explicitly state that this is a preliminary step before querying, though that is strongly implied.

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 schema description coverage is trivially 100%. Per the rubric, a null-parameter tool gets a baseline of 4. The description does not need to explain parameters and does not add anything misleading.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'Describe' and the specific resource 'power.interconnection_queue_spp', and enumerates the types of information covered (filters, groupings, metrics, detail fields, citation fields). This distinguishes it from sibling describe tools for other datasets.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage: call this tool to learn the valid fields before querying the SPP dataset. However, it does not explicitly state when to use this tool versus alternatives (e.g., the generic describe_power_interconnection_queue_v1 or other region-specific describe tools), nor does it provide any exclusion 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 indicate a safe, read-only, idempotent operation. The description adds the specific scope of the metadata (filters, groupings, metrics, detail fields, citation fields), which outlines what the agent can expect. It does not contradict any annotations, though it adds no further behavioral context like auth or rate limits, which are likely unnecessary.

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 concise sentence that front-loads the verb and resource, then lists the covered items. No wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the simple nature of a describe tool and the presence of an output schema, the description is sufficient. It enumerates the metadata categories and the title resolves the MISO specificity. It does not explicitly connect to the query tool, but that is not required for a describe operation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero parameters, so the description's role is minimal. The baseline of 4 applies; the description correctly lists the metadata categories rather than attempting to document nonexistent parameters.

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 the specific verb 'Describe' with a clear resource ('power.interconnection_queue') and enumerates the exact types of information it provides (filters, groupings, metrics, detail fields, citation fields). The title distinguishes this as the MISO-specific describe tool, differentiating it from regional 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 description implies its usage: it provides metadata needed before querying the dataset. However, it does not explicitly state when to use this tool over the other regional describe tools, nor does it reference the corresponding query tool. The title adds regional context but no explicit exclusions or alternatives are given.

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, idempotentHint=true, and destructiveHint=false, which cover safety and idempotency. The description adds that the tool yields exact-fact citations, but this is minor behavioral context. No contradictions.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

The description is a single, concise sentence that immediately conveys the tool's purpose. No wasted words, and it is front-loaded with the key action and resource.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given zero parameters and the existence of an output schema, the description adequately covers what the tool does. It provides enough context for the agent to understand the tool's role without needing additional details.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero parameters, so the schema covers all needed input. The description adds value by hinting at the output nature (facts, units, coverage, citations), but this is not parameter-related. Baseline 4 for zero parameters.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description explicitly states the tool describes native-XBRL Form 1 plant-cost facts, units, coverage, and exact-fact citations. The verb 'describe' plus the specific resource 'power plant costs' clearly distinguishes it from siblings focusing on other domains (e.g., AI infrastructure) or query 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?

No guidance is provided on when to use this tool versus alternatives, such as the many query_* or other describe_* tools. Given the large set of siblings, explicit usage directions would help the agent select the correct tool.

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

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

Annotations already declare read-only, idempotent, and non-destructive behavior. The description adds the scope of what is described (valid filters, groupings, etc.), which is useful but does not disclose additional behavioral traits such as return format or whether it lists all possible values. The bar is lowered due to annotations, and this meets it without exceeding.

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, concise sentence that is front-loaded with the verb and resource. Every word earns its place; there is no redundancy or fluff.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a describe tool with no parameters, the description fully covers what it does and what content it returns. The output schema exists, so return values need not be explained. Combined with annotations and the sibling query tool context, the description is complete and unambiguous.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

There are no parameters (0 params), so the baseline is 4. The description adds meaning by explaining the tool's output scope, but no parameter semantics are needed. The schema coverage is vacuously 100%.

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 verb ('Describe') and resource ('power.price_ercot'), and enumerates the exact types of information covered (filters, groupings, metrics, detail fields, citation fields). This clearly distinguishes it from other describe tools for different datasets and from the corresponding query 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 description implies its usage context: before constructing queries, users need to know valid filters, groupings, etc. There is no explicit 'use when' statement or alternative exclusion, but the context is clear given the sibling query tool for the same dataset. Not explicit enough for a 5.

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, idempotentHint, and non-destructive behavior. The description adds valuable context by specifying the exact categories of fields the tool will return (filters, groupings, metrics, detail fields, citation fields), setting expectations for the response content beyond safety traits.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

The description is a single, well-structured sentence that front-loads the core purpose and enumerates the categories precisely. There is no fluff or redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool has no parameters, has an output schema (not shown but present), and the description clearly covers the dataset and information categories, it is fully complete for its role. There are no gaps that impede 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 tool has zero parameters and the input schema is empty, so schema coverage is complete. The description does not need to explain parameter semantics since none exist. This aligns with the baseline of 4 for tools with no parameters.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: it describes valid filters, groupings, metrics, detail fields, and citation fields for the power.retail_sales dataset. This is a specific verb+resource combination that distinguishes it from sibling describe tools for other datasets.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage context by enumerating the types of information it will provide (filters, groupings, metrics, etc.), signaling it is a schema-discovery tool for power.retail_sales. It does not explicitly mention when to use it versus alternatives, but the sibling tool naming makes the appropriate use inferable.

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

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

Annotations already declare the tool as read-only, idempotent, and non-destructive. The description adds no behavioral context beyond what 'describe' naturally implies, such as any constraints, output details, or relationship to query tools. It does not contradict annotations but adds no extra transparency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

The description is a single, concise sentence that front-loads the action and lists the specific categories of information. Every word contributes meaning, with no redundancy or 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 the tool has no parameters and an output schema exists, the description is largely complete. It names the specific resource and the types of metadata provided. However, it relies on the title to convey the dataset's subject ('share of plants using robots...'), so it is slightly less self-contained.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero parameters, so the baseline is 4. The description does not need to explain parameters, and the schema coverage is 100% (empty). The mention of what is described (filters, metrics, etc.) adds contextual value even though there are no parameters.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's function: to describe valid filters, groupings, metrics, detail fields, and citation fields for the robotics.adoption dataset. It uses a specific verb ('Describe') and names the resource, distinguishing it from sibling describe tools for other datasets.

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 usage is implied: it is a describe tool paired with query_robotics_adoption_v1, meant to provide metadata before querying. However, the description does not explicitly say when to use it over alternatives or mention the companion query tool, so it only partially guides usage.

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, idempotentHint=true, and destructiveHint=false, so safety is covered. The description adds behavioral context by specifying what the tool returns: a description of valid filters, groupings, metrics, detail fields, and citation fields. This goes beyond the annotations by outlining the tool's output content, but it does not mention potential nuances like whether the output is a schema or a textual summary. No contradiction with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

The description is a single sentence that is front-loaded with the action ('Describe') and the resource ('robotics.trade'), followed by a concise list of what is described. Every word earns its place; there is no redundancy or filler. This is an ideal level of conciseness.

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 description tool with no parameters and an output schema present, the description is complete. It enumerates all categories of information the tool provides (filters, groupings, metrics, detail fields, citation fields), which fully satisfies the need to understand what the tool outputs. The presence of an output schema means return values are already documented, so the description does not need to elaborate further. The tool is simple enough that no additional context is required.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero parameters, so the baseline score is 4 as per the rubric. The description does not need to explain parameter semantics because there are none. The empty input schema is consistent, and the description focuses on the output aspects rather than inputs, which is appropriate for a describe tool.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: 'Describe valid filters, groupings, metrics, detail fields, and citation fields for robotics.trade.' This is a specific verb ('Describe') with a clear resource ('robotics.trade') and enumerates the exact scope of the description. The title adds further context by specifying 'industrial-robot imports, value + robot counts', distinguishing it from sibling describe tools for other datasets.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear context on when to use this tool: when one needs the valid filters, groupings, metrics, etc. for the robotics.trade dataset. It does not explicitly name alternatives or exclusions, but the resource-specific naming ('robotics.trade') and the presence of sibling describe tools for other datasets make the intended usage unambiguous. The lack of explicit 'instead of' language prevents a score of 5.

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, idempotentHint, and destructiveHint. The description adds that the tool describes query facets (filters, groupings, metrics, etc.), which is useful but does not disclose additional behavioral traits like output format or error handling. No contradiction with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

The description is a single concise sentence that front-loads the verb and resource. Every word earns its place, with no redundancy or 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 describe tool with no parameters and an output schema, the description fully covers the tool's scope by enumerating what it describes (filters, groupings, metrics, detail fields, citation fields). No additional context is needed.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero parameters, so the baseline is 4. The description accurately represents the tool's no-input nature and describes what it returns conceptually, which is sufficient for a describe tool.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: to describe valid filters, groupings, metrics, detail fields, and citation fields for the specific dataset 'space.satellite_filings'. This is a specific verb+resource that distinguishes it from sibling describe tools for other datasets and from the corresponding query 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 description implies the tool is used to discover query options for satellite_filings, but it does not explicitly state when to use it (e.g., before running queries) or contrast it with query_space_satellite_filings_v1. Usage is implied rather than explicitly guided.

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, idempotentHint, and non-destructive. The description adds valuable behavioral details: it verifies the raw workbook SHA-256 before returning source-header row values, and states that it proves the number with no re-query. This goes beyond the annotations without contradicting them.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

The description is about 80 words and front-loaded with the core purpose. Each subsequent sentence adds necessary context: input shapes, verification behavior, and use case. No redundant 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?

Despite minimal schema, the description covers the purpose, input requirements, and behavioral outcome (verified source-row values). An output schema exists, so the description need not enumerate return fields. It is complete for an agent to select and invoke 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 input schema is nearly empty (params is an arbitrary object/null, 0% coverage). The description fully compensates by specifying exactly what to pass: a citation object from either citations[ref].verify or a detail record's citation from include_records. This is critical semantic information not present 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?

The first sentence clearly states the action and target: 'Fetch and hash-verify the raw source row behind a returned citation.' It uses a specific verb and resource, and distinguishes from sibling query/describe tools by focusing on evidence retrieval for a citation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly says when to use it: 'Use this when an agent must prove an answer from the underlying source row.' It also explains the two input shapes from query tools, providing clear context. It doesn't explicitly list alternatives or exclusions, but the use case is unambiguous.

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, idempotentHint, and destructiveHint, but the description adds critical behavioral context: the tool's list grows over time, client tool lists are cached, and anything listed is reachable via query_capability_v1 even if the agent's current tool list predates it. This explains dynamic behavior and cache staleness, going beyond what annotations provide. No contradiction found.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

The description is two sentences long, front-loaded with the primary purpose, followed by essential usage caveats. Every sentence adds value; there is no wasted words or redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool has no parameters, has an output schema (covering return values), and annotations cover safety, the description provides sufficient context: purpose, when to use, and caveats about cache growth and capability availability. It is complete for an agent to decide when and how to invoke it.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool takes zero parameters (schema coverage 100%), so there are no parameter semantics to explain. Per the rubric, 0 params warrants a baseline of 4. The description adds no parameter-related information, but none is needed given the empty schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's function: 'List available exascale.build data capabilities for agent discovery before querying.' It uses a specific verb (list) and resource (exascale.build data capabilities), and distinguishes itself from sibling tools by framing it as a discovery step before querying. It also references query_capability_v1, clarifying how it relates to the broader toolset.

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?

Explicit guidance is provided: call this 'before querying' and 'BEFORE stating that a capability is not available.' It explains when the tool is necessary due to client tool lists being cached and the capability surface growing. It also implies using query_capability_v1 as the follow-up for reaching listed capabilities, giving a clear workflow.

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, idempotentHint=true, and destructiveHint=false. The description adds substantial behavioral context beyond these: monthly data cadence, 2014-01 start, Census revision vintage semantics via as_of, category/basis distinct-series behavior, non-additivity warnings, aggregation scope notes, and citation/row-level record behavior. No contradiction with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

Although long, the description is densely informative and excellently structured: opening purpose, explicit usage trigger, filter/parameter walkthrough, example, category/basis semantics, caveats, and exclusions. The formatting uses short paragraphs and bullet-like enumerations that make scanning easy, and every sentence contributes necessary operational detail.

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, minimal schema, and broad sibling set, the description is remarkably complete. It covers return behavior (JSON aggregates, citations, row-level records), data semantics, aggregation pitfalls, revision handling, and boundary exclusions. The presence of an output schema means return-value explanation is not required, and the description still adds plenty of 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 coverage for the single generic params object is 0%, so the description must fully document parameters. It does: it names category, basis, data_month, data_month_from/to, year, revision_status, group_by, and include_records, explains allowed values, gives a flat-structure rule, and provides concrete JSON examples. This is far beyond typical compensation for an opaque 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 opens with a specific verb and resource: 'Query verified U.S. private construction spending ($ millions) for data centers and semiconductor/computer-electronics manufacturing plants, from the U.S. Census Bureau's Value of Construction Put in Place (C30).' This precisely distinguishes it from sibling query_ai_infrastructure_* tools (employment, equipment trade, production, trade) and from power.* tools by explicitly scoping to construction spending.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly states when to use the tool: 'Use this for "how much is being spent BUILDING data centers (or chip fabs) in the US" questions.' It also gives clear exclusions and alternatives, e.g., 'use the power.* capabilities for capacity and the interconnection queue,' and lists many non-covered topics such as investment totals, MW capacity, and operator breakdown.

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 description reveals critical behavioral traits beyond annotations: QCEW data lag, NAICS vintage redefinition causing level shifts, suppression of confidential cells served as NULL, establishment-based job counting (not worksite), and non-additivity across hierarchy/time. These caveats are essential for correct interpretation and far exceed the basic readOnly/idempotent annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

The description is long but well-structured with clear sections and bullet-like lines. Every paragraph adds essential caveats (suppression, vintage, additivity), but some repetition could be trimmed for efficiency. Still, the organization makes it navigable and the length is justified by the data complexity.

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 is exhaustive, covering purpose, parameters, output behavior, suppression handling, NAICS vintage issues, measures, geographic scope, and explicit limitations. Given the tool's complexity and the presence of an output schema, it does not need to describe return values—everything else is comprehensively addressed.

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 only provides a generic 'params' object with no property definitions, so the description carries the full burden of parameter semantics. It thoroughly enumerates and explains industry_code values with agglvl mappings, own_code options, geography fields, time filters, group_by fields, and include_records, including concrete examples. This fully compensates for the absent schema coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool queries verified U.S. employment, establishments, and wages from BLS QCEW, specifically for data centers and semiconductors. It distinguishes itself from siblings by focusing on employment data and clarifying it is not an 'AI jobs' count, while also outlining two distinct families of questions it answers.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly specifies when to use the tool for two families of questions (industry employment and place-based county impact) and provides detailed filtering instructions with industry_code, agglvl, own_code, geography, and time parameters. It also clearly states what the tool does not determine (e.g., MSA, occupation, site headcount), giving strong usage boundaries.

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

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

Beyond the readOnly/idempotent annotations, the description discloses the return format (JSON aggregates with citations, optional row-level records), the exact behavior when summing overlapping rows (returns a country_aggregation note and nulls metrics), the fact that values are customs value not CIF/duty, the preliminary nature of recent months, and the data's re-verifiability via get_source_evidence_v1. This is rich behavioral context.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

The description is long but well-organized and front-loaded with a purpose sentence. Every section provides necessary detail given the tool's complexity, though there is a minor redundancy (e.g., mentioning the lack of vendor/tool-type breakdown in two places). It could be slightly tightened but remains efficient.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity, empty parameter schema, and rich annotations, this description is fully self-contained. It covers parameter semantics, provides examples, explains overlapping-group double-counting risks, defines the available measures, and clarifies the data's scope (origin country, imports only, preliminary revisions). The agent has everything needed to invoke the tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema is effectively an empty `params` object with 0% coverage and no property definitions. The description fully compensates by detailing all filter and grouping parameters (country, cty_code, country_level, year, data_month, ranges, group_by, order_by, top_n, include_records), explaining allowed values and giving concrete examples. It leaves no ambiguity.

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 precise statement: it queries verified U.S. monthly imports of semiconductor-manufacturing equipment (HS-8486) with customs value by country of origin from Census data. It explicitly contrasts this with the construction and chip-import sibling tools, naming them and explaining the fab lifecycle roles. The tool name also clearly indicates this is the query variant.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly says 'Use this for... questions' and names the alternative tools (ai_infrastructure.construction, ai_infrastructure.trade) with a clear division of responsibilities. It also provides strong guidance on how to interpret results and warns against summing across country rows due to overlapping groupings, giving the agent clear context for when and how to use the 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?

Despite annotations already declaring read-only/idempotent/non-destructive, the description adds substantial behavioral context: measures are intensive and averaged not summed, capacity/utilization are SA-only with structurally absent NSA cells, averaging across bases triggers a production_aggregation note, no breakdowns by state/fab/company, revisions are as_of tagged, and citations are re-verifiable. This goes far beyond the annotation safety profile.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

The description is long (several paragraphs) but densely packed with essential information that compensates for the absent schema detail. It is logically structured: what, when to use, parameters, examples, behavior, limitations. While some sentences could be tightened, the length is justified given the tool's complexity and the lack of schema-level parameter documentation.

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 opaque schema (0% coverage), and the rich annotations, the description is remarkably complete. It explains return aggregates, averaging behavior, data grain (monthly only, not quarterly/annual), limitations, and revision handling. It even notes the absence of state/county/fab/company breakdowns. There is little the agent would need to guess.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema is effectively opaque (only a params object with additionalProperties), but the description fully compensates by enumerating all filter parameters (series_kind, series_name, basis, year, data_month, data_month_from/to, group_by, include_records), their valid values, and giving concrete examples like {"series_kind": "capacity_utilization", "group_by": ["data_month"], "data_month_from": "2024-01-01"}. This provides complete semantic meaning beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a precise, specific verb+resource: 'Query verified U.S. semiconductor & electronic-component PRODUCTION and CAPACITY UTILIZATION — the Federal Reserve's monthly G.17 industrial-production index (2017=100) and capacity-utilization rate (percent) for NAICS 3344 — from the Board's own release, history to 1972.' It clearly distinguishes this tool from siblings by positioning it as the OUTPUT leg of the fab lifecycle, contrasting with construction, equipment trade, and imports.

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?

Explicit when-to-use guidance is provided: 'Use this for "are the domestic fabs actually producing / how hot are they running" questions.' It names alternatives (ai_infrastructure.construction, ai_infrastructure.equipment_trade, ai_infrastructure.trade) and clarifies the NAICS scope difference from QCEW's 334413, helping the agent choose correctly among siblings.

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

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

Beyond the annotations (readOnly, idempotent, non-destructive), the description discloses return format ('JSON aggregates with citations and optional row-level records'), the double-counting pitfall ('NEVER SUM across country rows'), the meaning of country as origin rather than installation, that imports are not exports, customs value not landed/CIF/duty, and that recent months are preliminary. This is exemplary behavioral context.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

Despite being lengthy, the description is well-structured: purpose, usage examples, parameter details, measures, and critical caveats are separated logically. Every sentence adds necessary information, especially given the zero-coverage schema. No filler or redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool is complex, but the description covers all dimensions: what data is returned, how to filter/group/order, which measures exist, why summing is wrong, the absence of quantity data, and citation/verifiability. With an output schema present and this rich description, an agent can confidently select and invoke the tool without guessing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema is a generic `params` object with additionalProperties true, so schema coverage is 0%. The description compensates fully by enumerating all meaningful parameters (`country`, `cty_code`, `country_level`, `year`, `data_month`, `data_month_from/to`, `group_by`, `order_by`, `top_n`, `include_records`), specifying formats and allowed values, and stressing that parameters must be flat top-level keys. This is far more useful 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?

The description opens with a precise statement: 'Query verified U.S. monthly IMPORTS of integrated circuits (HS-8542) — customs value (USD) by country of origin — from the U.S. Census Bureau's International Trade data.' This names the exact verb, resource, and scope. It also differentiates from siblings by clarifying that HS-8542 covers ALL integrated circuits and is NOT AI-accelerator/GPU-specific.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly states 'Use this for "how much $ of chips did the US import... and how is it trending" questions' and provides two complete example invocations for top source countries and national trend. It also gives a clear when-not-to-use signal: 'NOT AI-accelerator / GPU-specific.' This goes far beyond vague applicability.

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/idempotent/non-destructive behavior; the description adds that the output matches the named tool's cited envelope (same rows, citations, as_of), which is valuable. No contradiction with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

Three well-organized sentences load purpose, parameter semantics, and return behavior without fluff. Front-loaded with the core purpose and supported by a concrete example.

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 generic tool with two parameters, an output schema present, and rich annotations, the description covers purpose, dispatch semantics, parameter format, prerequisite discovery, and output equivalence. No significant 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 description coverage is 0%, but the description thoroughly explains both parameters: capability accepts either a capability id or a query primitive name, and params is the same flat JSON object the named query tool accepts. A concrete example and the describe_capability_v1 prerequisite are provided.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Clearly identifies 'Query any served capability by name' and frames itself as the generic twin of the named query tools, reaching capabilities not in the cached tool list. This distinguishes it from the many sibling query_* 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?

States it is the generic twin of the named query tools and can target any capability, including ones newer than the client's cached list, implying use when no named tool exists or the list is stale. It explicitly recommends calling describe_capability_v1 first for valid filters, but does not formally state when not to use it.

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

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

The description richly discloses behavior beyond the readOnly/idempotent annotations: the exact formula, auto-aligned scope from both sources, nameplate basis, storage exclusion, month-matched snapshot, coverage declaration, citation to both source rows, and explicit non-capabilities. This is far more than the annotations alone provide.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

The description is dense but well-organized: purpose, required input, formula, optional parameters, return values, and limitations. Every sentence adds useful detail, and there is no fluff or repetition of trivial 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?

Given the sophisticated multi-source calculation and minimal schema, the description covers all necessary aspects: input format, computation scope, returned outputs, error behavior, and boundaries. The presence of an output schema means it does not need to enumerate every return field, but it still summarizes what to expect.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema is an opaque `params` object with zero property documentation, so the description carries the entire burden. It explicitly documents `data_month` with format and example, optional `group_by` values, and `state`/`fuel_group` filters, making the parameters fully understandable.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description starts with a clear verb-resource pair ('Query verified U.S. capacity factor') and immediately explains the computation: joining EIA-860M capacity and EIA-923 generation. It distinguishes itself from sibling tools like describe_capacity_factor_v1 by emphasizing the querying/computation nature and the specific data sources, even without naming alternatives 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?

The description gives concrete usage guidance: requires `data_month`, tells the agent to ask for a month if absent, warns against blind retries on uncovered months, and describes optional grouping/filtering. It does not explicitly say 'use this instead of X when...' but provides clear operational context and lists limitations that imply when not to use it.

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

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

Annotations already indicate read-only, idempotent, non-destructive. The description adds significant behavioral detail: null handling with explicit price_status='source_missing', no unit mixing (mixed-unit aggregations are null), immutable capture vintages with as_of, and SHA-256 source evidence. These go far beyond the annotations and inform correct usage.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

The description is dense but well-organized: an initial summary, then atom-specific details, filtering, and caveats. Every sentence contributes a distinct constraint or behavior. The length is justified by the tool's complexity, and the front-loaded first sentence delivers the core purpose immediately.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool has two distinct data series with different units, null semantics, revision handling, and evidence requirements, the description covers all critical aspects. An output schema exists to document return structure, so the description need not repeat that. It explains unit-mixing pitfalls, proxy exclusion, and source-verification features fully.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema is a generic 'params' object with additionalProperties and 0% coverage. The description compensates fully by defining the two atom values, listing filterable fields (date, date_from/date_to, series, state, price_status, as_of), and giving a concrete example: {"atom":"state_electric_power_monthly","state":"TX"}. This is essential meaning not available 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?

The description opens with a specific verb+resource statement: 'Query verified EIA natural-gas price records from two public series.' It then distinguishes the two atoms (henry_hub_daily_spot and state_electric_power_monthly) and gives concrete examples, making it clear this is a data-returning query tool rather than the sibling describe 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 description provides detailed guidance on when to use each atom, how to filter (date, state, series, price status), and explicitly states what the tool does not do (no proxies, no heat rates, no unit conversion). It does not explicitly mention the describe sibling for metadata, but the usage boundaries are well-defined.

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?

Discloses behavioral traits beyond annotations: raw fraction format, exact owner-name matching without normalization, EIA convention for omitted generators, and citation with SHA-256 verification. Annotations (readOnlyHint, idempotentHint, destructiveHint) are consistent with the description.

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?

Well-structured with front-loaded purpose and detailed sections. Length is justified by the complexity of EIA conventions and filtering options, but could be slightly more concise.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity of the domain (EIA ownership conventions, verification), the description covers all necessary aspects: return values, filtering, edge cases (absent generators), and data provenance. The presence of an output schema is noted, but the description adds valuable 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?

Despite 0% schema description coverage, the description lists all filterable fields (plant, generator, owner name, state, etc.) with an example, fully compensating for the sparse schema. It adds meaning beyond the generic 'params' 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?

Clearly states it queries verified annual EIA-860 generator ownership, specifying the resource (power asset ownership) and output (raw owner names and shares). Distinguishes from sibling query_ tools by focusing on ownership 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?

Provides explicit filtering options (plant, generator, owner name, state, etc.), an example query, and critical EIA convention details about which generators appear. Gives clear guidance on when to use and what to expect, including the absence of fabricated rows.

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, idempotentHint=true, and destructiveHint=false, covering safety. The description adds content details ('cited', 'storage variants', 'suppression atoms') but does not disclose response format, pagination, or citation behavior. This is acceptable given annotation coverage but lacks deeper behavioral context.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

The description is a single, front-loaded sentence that efficiently names the verb and resource without redundant words. It is appropriately sized for a simple query tool, though the jargon ('suppression atoms') could be clearer.

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 opaque params object, no parameter schema, and no usage guidance, the description is incomplete for an agent to invoke the tool correctly. It describes the data content but not how to query it or when to choose it over siblings. The presence of an output schema covers return values, but the invocation 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?

The input schema defines only a free-form 'params' object with additionalProperties:true and no specific properties; schema description coverage is 0%. The description does not explain how to pass query parameters or what filters are available (e.g., date, season, unit type), leaving the agent with no guidance on how to construct a valid call.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states a specific verb ('Query'), a specific resource ('MISO Schedule 53 class-average and indicative-DLOL seasonal accreditation ratios'), and distinguishes it from siblings like query_power_capacity_accreditation_pjm_v1 and describe_* tools by naming the MISO-specific data and its components.

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?

There is no explicit guidance on when to use this tool versus alternatives. The description does not mention exclusions, alternative tools, or context like 'use this for raw data' vs 'describe' tools. The query/describe distinction is only implied by naming, not 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 declare readOnlyHint, idempotentHint, and non-destructive behavior, so the description need not repeat those. It adds valuable context about document separation and lack of reconciliation, which is not captured by the annotations and materially affects how results should be interpreted.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

Two concise, well-structured sentences. The main action and resource are front-loaded, and the second sentence adds a critical caveat without unnecessary 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?

The tool has an output schema, so the description correctly focuses on query dimensions and behavioral caveats. It covers the key facets and the non-reconciliation nuance. The 'internal' qualifier from the title is not carried into the description, and usage alternatives are not addressed, but overall it is sufficiently complete for a query tool with strong annotations.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema is a generic 'params' object with no property descriptions and 0% schema coverage, so the description carries the burden. It names four meaningful filtering dimensions (document kind, auction, delivery year, resource class), which gives the agent concrete guidance on what to pass. It stops short of defining parameter names or required/optional status, but this is adequate for a flexible query tool.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool queries cited PJM marginal ELCC class ratings, with specific filtering dimensions (document kind, auction, delivery year, resource class). This distinguishes it from sibling describe_ and query_ tools by naming a unique resource and operation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage context through the caveat that preliminary, final, and incremental-auction documents remain separate and unreconciled, but it does not explicitly say when to use this tool versus the sibling describe_power_capacity_accreditation_pjm_v1 or other query tools. No alternatives are named.

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, idempotentHint=true, and destructiveHint=false, so the safety profile is clear. The description adds useful context about data provenance and scope with words like 'cited', 'verbatim', and 'published'. No contradiction with annotations is present.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

The description is a single front-loaded sentence with no filler. It efficiently communicates the action, resource, and key data categories, earning every word's place despite heavy use of acronyms.

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 output schema exists and annotations are strong, but the tool's domain complexity (MISO capacity market, seasonal and zonal dimensions) and the complete lack of parameter guidance make the description insufficient for targeted invocation. The listed data elements help establish scope but omit how to select time periods or zones.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema exposes only a generic 'params' object with additionalProperties=true and zero property descriptions; schema coverage is 0%. The description does not explain how to specify query filters for ACP, ERZ values, CONE parameters, or IMM thresholds, leaving the agent without guidance on how to construct a valid request.

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 the specific verb 'Query' and clearly names the resource: MISO Planning Resource Auction results. It enumerates distinct data elements (seasonal zonal ACP, verbatim ERZ values, published CONE parameters, IMM conduct thresholds), which sharply distinguishes it from sibling describe_* tools and other query 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?

No explicit guidance is given on when to use this tool versus the sibling describe_power_capacity_market_miso_v1 or query_power_capacity_market_pjm_v1. The 'Query' verb and tool name imply it is for retrieving actual data rather than metadata, but no alternatives or exclusions are 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 declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is known. The description adds the 'cited' qualifier, indicating results include evidence references, and 'internal' in the title, but it does not disclose additional behavioral traits such as pagination, rate limits, or response size. The added context is useful but minimal.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

The description is a single, focused sentence with the verb front-loaded. Every phrase adds value, and it avoids repetition of the tool's name or title. It is compact yet information-dense.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool has an output schema (not shown) and simple input requirements, the description provides the core domain context: what data fields are available and by which filters. It does not explain how to construct parameters or handle edge cases, but for an internal query tool with minimal expected complexity, it is largely sufficient.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema is essentially empty (anyOf object/null with additionalProperties true), providing zero parameter names or types. The description compensates by stating the logical filtering dimensions 'by delivery year and LDA', which informs the agent what inputs matter. It does not specify exact parameter names or formats, but the guidance is meaningful for a 0% coverage 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 opens with the specific verb 'Query' and clearly identifies the resource as 'PJM Base Residual Auction' results, listing exact data points (UCAP clearing prices, RTO cleared MW, reliability requirement, administrative price collar) and dimensions (delivery year, LDA). This distinguishes it from sibling query tools that target other PJM or power-market metrics.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description clearly implies the tool is for obtaining cited PJM RPM auction results, which gives clear context for when to use it. However, it does not explicitly mention alternatives (e.g., 'use describe_power_capacity_market_pjm_v1 for metadata') or exclusions, so it stops short of full 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?

The description reveals key behavioral details beyond annotations: the lifecycle selector parameter (operating/planned/retired/canceled) and the fact that there is no status/status_group parameter (a common confusion). It also notes the return format (JSON aggregates with citations, optional generator-level records) and explicitly states what it does not compute. Annotations already declare read-only/idempotent, so this adds context without contradicting.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

The description is long but each part serves a purpose: core purpose, usage criteria, scope exclusions, and alternative tools. It is front-loaded and structured, with no filler words or repetitive content.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Despite the minimal schema, the description provides enough to correctly invoke the tool: it explains the params pattern, the lifecycle default, and the optional records flag. The output schema likely covers return structure. It also situates the tool among siblings, making it complete for an agent to select and use.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema only has a generic params object with no property definitions (0% coverage). The description compensates by enumerating acceptable filter keys (state, county FIPS, balancing authority, fuel, prime mover, technology, lifecycle, year) and mentions include_records. It also clarifies the default lifecycle value. However, it doesn't provide detailed value formats or the full set of possible keys, so while it's strong, it falls short of exhaustive.

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, multi-faceted statement: 'Query verified U.S. generator-level operating, planned, retired, or canceled power capacity from EIA-860M.' This clearly identifies the action (query), resource (generator-level power capacity), and scope (U.S., lifecycle status). It also lists distinguishing filter dimensions (state, county FIPS, balancing authority, fuel, etc.) that separate it from sibling tools like generation or interconnection queue.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly states 'Use this for capacity questions...' and then provides a clear list of exclusions ('Does not determine electricity supplied, generation MWh, real-time dispatch, capacity factor...'). It also names specific alternative tools for interconnection queue queries. This is textbook when/when-not guidance with 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?

Beyond annotations (readOnly, idempotent, not destructive), the description adds critical behavioral traits: demand_mw is served verbatim, not a computed sum; inverted additivity with a respondent_aggregation scope note; source anomalies served verbatim and cited; default_latest_day behavior; and as_of vintage pinning. No contradictions with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

Though lengthy, the description is appropriately sized for the tool's complexity. It front-loads the core purpose in the first sentence and organizes information into clear thematic sections (scope, parameters, data provenance, additivity, exclusions). Every sentence delivers operational value without fluff.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description covers data source, history range, parameter semantics, defaults, additivity caveats, data quality handling, and explicit exclusions with alternatives. An output schema exists, so return-level details are not needed here; the description is complete for selecting and invoking the tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema is nearly empty (only a generic params object, 0% coverage), so the description fully carries the load. It enumerates valid respondent values, data_date/hour_number combination, range parameters, group_by axes, flat params structure, and provides a concrete JSON example. It also explains which params are filters vs output axes.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description starts with a specific verb and resource: 'Query verified U.S. hourly electricity demand (MW) as EIA's own published national and regional totals from the EIA Grid Monitor (region-data).' It clearly distinguishes from siblings by stating this closes power.demand's refusal of national/region totals and that BA demand is non-additive.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly states when to use: 'Use this for "how much load for the whole country, or a region" questions.' It also provides exclusions with alternatives, e.g., 'Does not determine balancing-authority-level demand (use power.demand for the BA series)' and lists other tools for capacity, generation, retail sales, etc.

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 declare readOnlyHint and idempotentHint, and the description adds contextual behavior: default latest day when no calendar window, vintage/as_of semantics, empty_scope notes, and citation behavior. It discloses that demand is not additive and that BA aggregation produces scope notes plus omitted demand metrics.

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?

While the description is lengthy, every sentence contributes critical information for correct use, and the core purpose is front-loaded. The structure flows from purpose to usage, defaults, caveats, and exclusions, making it dense but efficient for the tool's complexity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With a free-form params schema and output schema present, the description covers all essential behavior: default windows, vintage handling, non-additivity, exclusions, and alternative tools. It effectively serves as the sole documentation for the tool's usage and edge cases.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema provides only a generic 'params' object with no property descriptions (0% coverage). The description compensates by enumerating filterable fields (balancing_authority_code, region, data_date, hour_number, datetime_utc, is_imputed, data_date_from/to), include_records, as_of, and group_by behavior, plus defaults and scope notes.

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: 'Query verified U.S. hourly electricity demand (MW) by balancing authority from EIA-930.' It clearly distinguishes from siblings by stating it does not compute rollups and names alternative tools for capacity, generation, and retail sales.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It explicitly states when to use ('how much load' questions at the hourly balancing-authority grain) and provides exclusions with alternative tools ('use power.capacity', 'use power.generation', etc.). It also warns against non-additivity across balancing authorities, giving clear guidance for correct usage.

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 description reveals important behavioral details beyond the readOnlyHint annotation: EIA withholds costs for some plants, the raw '.' marker is preserved in fuel_cost_raw, numeric cost is null, and fuel_cost_status reports 'withheld'. It explicitly states missing values are never zero or imputed, and that every quantity can be verified against its workbook cell.

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 information-dense yet well-structured: it opens with a clear purpose, then details filtering and data handling, closes with limitations. Every sentence adds value without redundancy. It is appropriately sized for the tool's complexity.

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 and the presence of an output schema, the description covers purpose, filtering options, data nuances, limitations, and verification. It leaves no significant gaps for an agent to misinterpret the tool's behavior or output.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Despite 0% schema description coverage, the description compensates thoroughly by listing all major filterable fields (plant, month/range, exact source strings, state, fuel, cost status, balancing authority code) and providing a working example. This gives the agent full parameter understanding.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool queries verified raw EIA-923 fuel receipts and costs, specifying it returns Page 5 Fuel Receipts and Costs rows with detailed fields. The verb 'Query' combined with the resource 'power_fuel_cost' and the contrast with sibling 'describe_power_fuel_cost_v1' make the purpose precise and distinguishable.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly states what the tool does not do (derive heat rates, efficiency, marginal cost, etc.) and advises combining raw atoms elsewhere for such analysis. It also provides a concrete filter example `{"state":"TX","balancing_authority_code":"ERCO"}`, giving clear guidance on usage context and 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 readOnly/idempotent/non-destructive, but the description adds valuable behavioral context: vintage handling, as_of semantics, empty_scope notes, BA data availability from 2018 onward, and citation details. No contradictions with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

The description is long but front-loaded with the core purpose and progressively adds essential detail. Some text could be tightened (e.g., repeating 'as_of' mechanics), but every sentence serves a functional purpose given the complex domain and opaque 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?

Despite the complex data domain and minimal schema, the description covers query scope, filtering dimensions, aggregation semantics, historical behavior, BA limitation, output format (JSON with citations), and exclusions. It is fully self-sufficient for an agent to select and invoke the tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema is opaque (only a generic params object with 0% property coverage), so the description carries the full burden. It explains the meaning and proper use of key parameters (fuel_group, energy_source_code, atom, data_month, as_of, balancing_authority_code) and warns about subtle aggregation pitfalls (coal split across codes, never sum across atoms), fully compensating for the schema gap.

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 opening sentence clearly states the tool queries verified U.S. monthly net electricity generation (MWh) from EIA-923, with a specific verb and resource. It further distinguishes itself from siblings by listing non-goals (capacity, demand, prices, etc.), making its purpose unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly states when to use the tool ('Use this for "how much was generated" questions...') and gives concrete selection guidance for fuel_group vs energy_source_code, atom selection, as_of pinning, and BA limitations. It also names alternatives (e.g., 'use power.capacity') for non-generation topics, satisfying the when/when-not criterion.

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

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

Annotations already declare read-only/idempotent, but description adds crucial behavioral context: net_mw_to_grid is REQUESTED capacity, not built; withdrawn-dominated; no built-MW column exists; never relabel as built. Also discloses citation behavior (source, as_of, source_row) and that no data-center type is inferred. No contradiction with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

The description is long but every sentence adds necessary value for a complex tool with a generic schema. It is front-loaded with purpose, then details fields, warnings, and alternatives, with no redundancy. The structure is logical and scannable.

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 and sparse schema, the description is complete: it covers return structure, grouping/filtering, citation verification, capacity semantics, ISO scope, and exclusions. Even with an output schema present, it adds valuable caveats (requested vs built) that are not inferable from schemas.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema is a generic free-form object with 0% coverage, so the description carries the full burden. It exhaustively lists filterable fields, grouping options, the flat-params requirement, and provides concrete examples. This fully compensates for the schema's lack of 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?

The description uses a specific verb ('Query') and resource ('CAISO generator interconnection queue'), and explicitly names the ISO and geographic scope. It distinguishes from sibling tools by naming alternative ISO queues (MISO, PJM, NYISO, etc.) and the capacity tool (query_power_capacity_v1).

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 extensive when-to-use guidance: CAISO-only, not for cross-ISO comparison, use query_power_capacity_v1 for built capacity, and enumerates sibling tools for other ISOs. Also explains scope by application_status (ACTIVE, COMPLETED, WITHDRAWN) and notes exclusions (e.g., current-cluster intake file, data-center type).

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?

Even though annotations already declare readOnlyHint, destructiveHint, and idempotentHint, the description adds crucial non-obvious behaviors: capacity_mw is requested (not installed), monthly snapshots with as_of floor at 2018-12, application_status derived from sheet membership, and that inactive/cancelled lists are not exhaustive. It also explains that earlier as_of before the floor is refused, which is beyond structured fields.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

The description is long, but it is organized into clear thematic paragraphs (returns, parameters, history, capacity caveat, status derivation, alternatives) and starts with the core purpose. While some redundancy exists (e.g., repeated emphasis on requested capacity and monthly publication), the length is justified by the tool's complexity and the need to prevent misuse.

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 all essential operational aspects: return format, citations, group/filter parameters, time-travel semantics, error conditions (floor refusal), and proper interpretation of queue MWs. With an output schema present, it need not enumerate every return field, but it does provide enough domain context to correctly invoke and interpret results.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema only exposes `params` as an untyped object with zero documentation. The description compensates thoroughly by documenting accepted top-level keys (application_status, fuel, technology, group_by, order_by, top_n, as_of, include_records, etc.) and providing concrete JSON examples for active solar and grouped fuel capacity. This fully bridges the schema's 0% 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 begins with 'Query the ERCOT generator interconnection queue' and specifically identifies the ERCOT GIS Report (EMIL PG7-200-ER), clearly distinguishing it from sibling ISO queue tools. It uses a precise verb and resource, with no ambiguity about what data is returned.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly names alternatives for each ISO (e.g., 'For MISO use query_power_interconnection_queue_v1; for PJM ...'), and directs users to query_power_capacity_v1 for built/operating capacity. It also states what the tool does NOT serve (large-load queue, data-center inference), providing clear 'when-to-use' 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?

Beyond annotations (read-only, idempotent, non-destructive), the description discloses that requested MW is not built capacity ('NEVER read a queue-MW total as installed or operating capacity'), that net_mw is a real value (not missing) for CNR-only requests, and that records include citation fields. It also distinguishes application_status from project_status, adding important interpretative context.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

The description is lengthy but each paragraph has a clear function: data scope, value semantics/caveats, and regional alternatives. It is front-loaded with the core purpose and uses structured enumeration. Some redundancy exists but overall it is efficiently organized.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with many undocumented parameters, the description covers filtering, grouping, value codes, geography, and caveats, and points to sibling tools for other ISOs. It also explains return citation behavior and the relationship to output schema, making it complete for an agent to select and invoke 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?

Despite zero schema parameter documentation, the description enumerates all filterable fields (application_status, request_type, fuel_type, zone, etc.), explains allowed values (e.g., 'A'=Active, 'C'=Commercial, 'W'=Withdrawn), and gives concrete parameter examples with flat top-level keys. It fully compensates for the schema's lack of detail.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.