Verified behind-the-meter data center power, announcements, and provenance receipts.
Scored across 4 tools
Each tool has a clear, distinct purpose: one for third-party announcements, one for dataset metadata, one for detailed facility dossiers, and one for searching facilities. No overlap in functionality.
All tools use lowercase snake_case with a verb_noun pattern. Three start with 'get_' and one with 'search_', which is a minor deviation but still predictable and readable.
With 4 tools, the server is well-scoped for a focused data access purpose—neither too few nor too many.
The tool surface covers the core use cases for a read-only behind-the-meter power facility data server: announcements, dataset summary, single facility retrieval, and search. A tool to list all facilities without a query is missing but largely covered by search.
Get the separately classified third-party reported project pipeline. These records are not BTW-verified operating capacity.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | ||
| state | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description discloses that the records are not BTW-verified operating capacity, which is a behavioral trait. However, with no annotations provided, additional transparency about permissions, side effects, or data freshness would be helpful. The description partially addresses 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 consists of two concise sentences that are front-loaded with the core purpose. It is efficient and avoids 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?
Given the tool has two parameters with no schema descriptions, no output schema, and no annotations, the description is insufficient to fully understand how to use the tool. It lacks parameter documentation and output format 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 description does not mention either parameter (limit, state). With schema description coverage at 0%, the description should provide meaning for these parameters, but it offers none. This is a significant 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 description clearly states the tool retrieves a 'project pipeline' that is separately classified and third-party reported, distinguishing it from sibling tools that focus on dataset summaries and facilities. However, the term 'project pipeline' is somewhat vague and could benefit from more specificity.
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, nor does it mention any prerequisites or exclusions. Agents would have to infer usage context from the tool name and sibling names alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get the canonical dataset date, verified fleet totals, methodology, license and citation.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It does not disclose any behavioral traits such as idempotency, side effects, rate limits, or authentication needs. For a read-only operation, more transparency is expected.
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 efficiently lists all key elements. No superfluous words, and it is front-loaded with 'Get the canonical dataset...'.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema, the description lists the main components of the summary. It could be more complete by mentioning the structure or that it returns a single object, but it covers the essential information for a simple getter.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
With zero parameters, the baseline is 4. The description adds meaning by enumerating the contents of the summary (date, fleet totals, methodology, license, citation), which goes beyond the empty schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description specifically lists the exact data points retrieved: canonical dataset date, verified fleet totals, methodology, license, and citation. This clearly distinguishes it from siblings like get_announcements and get_facility.
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 vs alternatives. The sibling names imply contexts (announcements, facilities), but the description doesn't state 'use this to get dataset overview; for facility details use get_facility'.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get one verified facility dossier including units, permits, quotes, source URLs, SHA-256 checksums and archived evidence links.
| Name | Required | Description | Default |
|---|---|---|---|
| slug | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must disclose behavior. It mentions the return contents but not traits like read-only nature, error handling (e.g., missing slug), rate limits, or side effects. The verb 'Get' weakly implies safety, but insufficient detail.
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, no redundancy, front-loaded with purpose and scope. Every word adds value.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple get operation with one parameter and no output schema, the description covers what the tool returns. However, it lacks details on output structure, error scenarios, and prerequisites (e.g., knowing the slug). Adequate but not comprehensive.
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 has 1 parameter (slug) with 0% description coverage. The tool description does not explain the slug parameter's format, purpose, or example, relying solely on the schema's minimal definition. This fails to add meaning beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Get') and resource ('verified facility dossier') and lists specific included data types (units, permits, etc.), distinguishing it from siblings like get_announcements.
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. It implies use for retrieving a single facility's full dossier, but does not discuss exclusions, prerequisites, or when to use sibling tools like search_facilities.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search BTW-verified behind-the-meter power facilities. Returns published facts and capacity; announcements are not included.
| Name | Required | Description | Default |
|---|---|---|---|
| query | No | Name, developer, offtaker, county or state text | |
| state | No | Two-letter US state code | |
| min_mw | No | ||
| status | No | Published facility status, for example operating |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden. It discloses that announcements are not included, but does not mention pagination, idempotency, rate limits, or other behavioral traits. The description is minimal for a search tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two concise sentences, front-loaded with the core action. It could benefit from a bullet list of parameters or a clearer structure, but it is 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 4 optional parameters, no output schema, and no annotations, the description is somewhat incomplete. It specifies the output scope but lacks details on search behavior (e.g., fuzzy matching), pagination, or error handling. Adequate but not thorough.
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 75% (3 of 4 parameters have descriptions). The tool description adds no extra parameter insight beyond stating the output type ('published facts and capacity'). The schema already handles parameter descriptions adequately.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states that the tool searches for 'BTW-verified behind-the-meter power facilities' and specifies that it returns 'published facts and capacity' while excluding 'announcements'. This distinguishes it from sibling tools like 'get_announcements'.
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 searching facilities and mentions what is not included (announcements), which hints at using get_announcements for announcements. However, it lacks explicit guidance on when to use this tool versus other siblings or any prerequisites.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
get_announcementsget_dataset_summaryget_facilitysearch_facilitiesCarbon-accounted agent compute: free footprints; certificates backed by real offset retirement.
Live power, energy, grid, gas, fiber + off-market data-center capacity in kW/MW — query and cite.
PJM/MISO energy arbitrage. Intel TDX attested, on-chain every 60 min. MCP tools for AI agents.
Live power, energy, grid, gas, fiber & data-center site-selection infrastructure — query and cite.
Add one secure layer between your agents and this server.
