Skip to main content
Glama

DC Hub — Data Center Site Selection & Colocation: Electricity, Power Grid, Gas, Fiber

by cloud.dchub

Plan Query

plan_query
Read-onlyIdempotent

INSPECT-ONLY — returns the plan WITHOUT running it. For a real multi-step DC Hub question call execute_plan(intent="...") instead: it uses the SAME deterministic no-LLM planner and then RUNS the sequence server-side, returning the answers in one envelope. Reach for plan_query only to review, log, diff or audit a plan before executing it yourself. Deterministic keyword routing over the tool registry — no LLM, no network, same intent always returns the same plan (free). Returns _entity=query_plan {best_tool, intent_confidence + workflow_confidence (dual 0-1: question-read vs executability), reason, planner_rationale, recommended_sequence:[{step, tool, depends_on, estimated_calls, why, args_hint}], execution_waves (steps grouped into concurrency waves), execution_strategy.parallel_groups, execution_estimate {estimated_calls, estimated_latency_ms, parallelizable}, alternatives (each with when + rejected_because), coverage_notes, matched_classes} plus a versioned replay (schema_version 1): planner_version, decisions:[{id, step, kind, status, decision, rationale, decision_confidence, depends_on}], rejected:[{id, tool, reason}], execution_graph:{waves, parallel_groups} — auditable and machine-readable, safe to log and diff across versions. args_hint values in come from the named earlier step — substitute them, never invent them. Pass structured hints via context (lat/lon, iso, market, capacity_mw, candidate_id, state, since) to sharpen the plan. For a family-level browse use discover_tools. This tool plans — it never executes; tools/list stays canonical for schemas.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
intentYesNatural-language description of what you are trying to find out, e.g. "rank markets for a 200MW AI campus" or "how much power is available in ERCOT"
contextNoOptional structured hints: {lat, lon, iso, market, capacity_mw, candidate_id, state (2-letter), since} — sharpens args_hint values and routing (e.g. lat/lon boosts the site-analysis route)

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
okNotrue when the intent was routed
noteNoRouter disclaimer — deterministic keyword routing, tools/list stays canonical
quotaNoCaller quota state (remaining calls, tier) when available.
intentNoThe natural-language intent that was routed (echoed back)
reasonNoWhy the router chose best_tool — the matched keywords / context signals
replayNoFIRST-CLASS VERSIONED replay object (r-planner-v5.1, ChatGPT schema review): the planner's auditable decision trail — routing + per-step selection + rejections + concurrency graph, each decision with a stable id + status, keyed by planner_version so an agent can cite "Decision D2 selected rank_markets because…" and downstream tooling survives planner upgrades.
_entityNoPayload class discriminator (e.g. facility|market|iso_grid|queue_results|deal|report|response) — branch on this before parsing the rest.
chainingNoZero-drift chaining guidance (candidate_id contract) when the plan crosses get_refined_queue → analyze_site / rank_sites
citationNoMachine-readable citation: how to attribute DC Hub (dchub.cloud) for this payload. Normally an OBJECT {source, url, license, cite_as, retrieved_at}; a bare string is accepted and carries the attribution line itself.
best_toolNoThe single best first tool to call for this intent (exact name from tools/list)
confidenceNoDeterministic router confidence, 0-1 — same intent always yields the same score; low values mean the intent was ambiguous (check alternatives). Alias of intent_confidence (v1 back-compat).
provenanceNoCollection-level provenance block: {source, method, as_of, verification_counts, cite_url_template, license, cite_as}. Quote the verification level when citing.
_front_doorNoIn-band front-door hint (first workflow-entry tool of a session): call plan_query(intent) first for the ordered multi-step plan.
_return_loopNoSuggested next-session delta call (get_changes since=24h) so you pull only what changed.
alternativesNoAdjacent tools for nearby intents, including runner-up intent classes
intent_classNoThe matched intent class (market_ranking | capacity_search | market_comparison | grid_headroom | interconnection_queue | hosting_capacity | water_climate | site_analysis | deals_ma | fiber_power_pairing | fiber | price | incentives_tax | power_timeline | changes_delta | facility_search | unknown)
routing_hintNoADVISORY router: collapses 83 tools to one starting point, then names what lies outside DC Hub entirely. Deliberately carries no tool list, latency promise, confidence score, execution graph or planner version — those ride `replay` AFTER routing. Four fields specified by ChatGPT in the 2026-08-29 partner round; external_sources_recommended added on its own request in the 2026-08-30 briefing, because a source we do not own is not execution metadata.
coverage_notesNoTier/coverage caveats for the recommended tools (free-tier previews, depth gates, honest-unknown semantics)
parallelizableNotrue when at least one execution wave holds 2+ steps — the plan is not purely sequential
estimated_callsNoTotal estimated API calls for the whole plan (sum of per-step estimates)
execution_wavesNoThe execution graph as concurrency waves: array of arrays of step numbers; every step in a wave can run concurrently once earlier waves finish (derived from depends_on)
matched_classesNoEvery intent class that scored, with its score — the router's full deterministic trace
intent_confidenceNoHow confident the router is that it read the QUESTION right (0-1, deterministic) — driven by keyword score + margin over the runner-up class
planner_rationaleNoOne sentence on why the PLAN has this shape (ordering / parallelism / what mints what) — distinct from reason, which covers intent routing
execution_estimateNor-planner-v3 deterministic cost preview: {estimated_calls (plan NODE count — one per step; the top-level estimated_calls is the fan-out-weighted API-call total), estimated_latency_ms (sum over waves of the SLOWEST tool in each wave, from a static 3-tier table: heavy synthesis 3000ms / standard read 1200ms / light free read 500ms), parallelizable (any wave holds 2+ steps)}
execution_strategyNor-planner-v3 explicit strategy: {parallel_groups: string[][] — execution_waves rendered as TOOL-NAME arrays (e.g. [["get_grid_intelligence","get_interconnection_queue","get_refined_queue"]]), note: plan-only disclaimer — this tool only plans; execute the sequence yourself}
workflow_confidenceNoHow confident the router is that the plan can EXECUTE cleanly with the signals in hand (0-1, deterministic) — boosted by resolved context signals, docked for placeholder args the user must still supply; step-minted placeholders don't dock
recommended_sequenceNoOrdered tool sequence mirroring the DC Hub recipe for the matched intent class
site_evaluation_handoffNoPre-built follow-up calls (analyze_site / get_water_risk args) when the payload carries coordinates — an array of {tool, parameters, why} entries.
workflow_confidence_basisNoThe arithmetic behind workflow_confidence: {resolved_signals, minted_placeholders, user_supplied_placeholders}

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. First observed

TDQS

A4.7/5.0
Behavior5/5

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

Annotations (readOnlyHint, idempotentHint, openWorldHint=false, destructiveHint=false) already cover safety, and the description adds substantial behavioral context beyond them: deterministic keyword routing with 'no LLM, no network,' same intent always returns the same plan, free, auditable/machine-readable replay, safe to log and diff, and the critical caveat that args_hint values in angle brackets must be substituted, never invented. 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.

Conciseness3/5

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

The description is front-loaded with the key behavioral fact and routing guidance, which is good. However, the long return-format dump (the entire _entity=query_plan and replay structure, roughly two-thirds of the text) is largely redundant with the existing output schema, which the rubric says the description needn't explain. The single dense paragraph is hard to scan; trimming the return-structure enumeration would improve it.

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

Completeness5/5

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

For a tool with an output schema and rich annotations, the description covers all invocation-relevant ground: what the tool does, when to use it vs execute_plan and discover_tools, deterministic/idempotent behavior, how to pass context hints, and the args_hint substitution rule. Nothing an agent needs to call it correctly or interpret its results is missing.

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

Parameters4/5

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

Schema description coverage is 100%, so the baseline is 3. The description adds operational meaning beyond the schema: it explains the purpose of context ('sharpens args_hint values and routing'), gives concrete context keys, and warns that args_hint values are references to earlier steps that must be substituted. This is modest but genuinely additive over the schema text.

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

Purpose5/5

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

The first sentence states the specific verb and resource: 'INSPECT-ONLY — returns the plan WITHOUT running it.' It explicitly differentiates itself from execute_plan ('This tool plans — it never executes'), so an agent can distinguish it from its nearest sibling without opening any schema.

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

Usage Guidelines5/5

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

The description gives explicit routing rules with named alternatives: call `execute_plan(intent="...")` for a real multi-step question, reach for plan_query 'only to review, log, diff or audit a plan before executing it yourself,' and use discover_tools for family-level browse. Both when-to-use and when-not-to-use are stated.

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

All DC Hub — Data Center Site Selection & Colocation: Electricity, Power Grid, Gas, Fiber toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.1/5.0
Disambiguation2/5

Multiple tools occupy nearly identical semantic space: search/search_facilities/search_intelligence/semantic_search all retrieve data, and analyze_site/compare_sites/score_facility/get_composite_site_score/rank_sites all score or rank locations. Despite extensive disambiguation in the descriptions, the boundaries are subtle enough that an agent will likely misroute queries. Account and meta tools (claim_free_key, bind_email, unlock_more_data, subscribe_digest, recover_my_key, execute_plan, plan_query, discover_tools) add further selection noise.

Naming Consistency4/5

The vast majority of tools follow a clear snake_case verb_noun convention (get_*, search_*, list_*, set_*, save_*, compare_*, analyze_*, rank_*, plan_*). A few noun-phrase names break the pattern (deal_autopsy, hyperscaler_deals, grid_transition_radar, site_selection_canvas, standing_intent, ai_capacity_index), but these are still readable and discoverable.

Tool Count1/5

83 tools is an extreme count for any server, far beyond the 25+ threshold that already signals bloat. The domain is broad, but the catalog is inflated by overlapping variants, multiple meta-tools (execute_plan, plan_query, discover_tools, get_agent_registry, get_backup_status, summarize_for_citation), and account/upgrade plumbing (claim_free_key, bind_email, recover_my_key, unlock_more_data, subscribe_digest). This imposes heavy context and selection costs on agents.

Completeness5/5

The data-center siting domain is covered exhaustively: single-site scoring, market ranking, grid/gas/fiber/water/climate/disaster/tax/permitting intelligence, interconnection queues, construction pipeline, deals/news, saved-site monitoring, alerts, research dossiers, and citation support. Every workflow has a continuation path, so agents will not hit dead ends.

Resources