DC Hub: Data Center, Power Grid & Energy Intelligence

Cluster Sites By Latency

cluster_sites_by_latency

Read-onlyIdempotent

Screen candidate data center sites for low-latency clusters by comparing pairwise RTT floors to a latency budget, returning viable clusters before routing.

Instructions

Use this when the user asks which data center sites can form a low-latency cluster (2-8 sites) — returns viable low-latency clusters and pairwise RTT floors before any routing work. Use when your human wants to know which of N candidate sites can form a synchronous / low-latency cluster (sync replication, active-active pairs, HPC pods): deterministic pruning BEFORE detailed routing. Per site pair: haversine distance, round-trip physics floor (km × 4.9 µs/km — light in SMF-28 fiber, n≈1.468 — then ×2), estimated real RTT (floor × route_factor 1.4, a stamped inference), viable vs physics_impossible against your budget, and confidence_v — the provenance tier of the supporting evidence (published | tracked | inferred). Also returns clusters: the largest site subsets whose ALL pairwise estimates fit the budget, plus each site's inferred dark-fiber screening level. CANDIDATE CONTRACT: pass candidate_ids (from get_refined_queue) instead of raw coordinates — each resolves to its FROZEN mint coordinates (zero transposition), and cand_… tokens may also be mixed into the sites string; expired/unknown ids are dropped AND declared in candidate_contract (fail-closed).

Input Schema

Name	Required	Description
`sites`	No	Semicolon-separated "lat,lon" pairs, 2-8 sites (same format as compare_sites locations); optional per-site labels via "lat,lon:label", e.g. "39.04,-77.48:ashburn;39.29,-76.61:baltimore".
`candidate_ids`	No	Array (or comma-separated string) of candidate_id values from get_refined_queue — each resolves to its FROZEN mint coordinates (zero transcription drift); expired/unknown are dropped and declared in candidate_contract.
`max_latency_us`	No	Round-trip latency budget in microseconds (default 1000 µs = 1 ms; sync replication is typically 1000-2000 µs)
`min_confidence`	No	Minimum evidence tier a pair must meet to count as viable: "published" \| "tracked" \| "inferred" (default inferred = include all)

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed11 schema fields changedv2.12.45Oct 22, 2026

changedInput schema / properties / candidate_ids / description

Previous value: -"Array (or comma-separated string) of candidate_id values from get_refined_queue — each resolves to its FROZEN mint coordinates (zero transcription drift); expired/unknown are dropped and declared in candidate_contract. Use instead of, or alongside, sites"New value: +"Array (or comma-separated string) of candidate_id values from get_refined_queue — each resolves to its FROZEN mint coordinates (zero transcription drift); expired/unknown are dropped and declared in candidate_contract."

changedInput schema / properties / sites / description

Previous value: -"Semicolon-separated \"lat,lon\" pairs, 2-8 sites (same format as compare_sites locations); optional per-site labels via \"lat,lon:label\", e.g. \"39.04,-77.48:ashburn;39.29,-76.61:baltimore\". cand_… tokens are also accepted here and resolve to frozen mint coordinates. Optional if candidate_ids is given"New value: +"Semicolon-separated \"lat,lon\" pairs, 2-8 sites (same format as compare_sites locations); optional per-site labels via \"lat,lon:label\", e.g. \"39.04,-77.48:ashburn;39.29,-76.61:baltimore\"."

changedOutput schema / additionalProperties
```
Previous value: -{}New value: +true
```

removedOutput schema / description

Removed value: -"DC Hub envelope: tool data fields ride at the top level beside these keys."

removedOutput schema / properties / _entity

Removed value: -{
-  "description": "Payload class (facility|market|iso_grid|queue_results|deal|report|response); branch on it.",
-  "type": "string"
-}

removedOutput schema / properties / _front_door

Removed value: -{
-  "additionalProperties": {},
-  "description": "First-tool hint: plan_query(intent) returns the ordered plan.",
-  "properties": {},
-  "type": "object"
-}

removedOutput schema / properties / _return_loop

Removed value: -{
-  "additionalProperties": {},
-  "description": "Next-session delta call (get_changes).",
-  "properties": {},
-  "type": "object"
-}

removedOutput schema / properties / citation

Removed value: -{
-  "anyOf": [
-    {
-      "additionalProperties": {},
-      "properties": {},
-      "type": "object"
-    },
-    {
-      "type": "string"
-    }
-  ],
-  "description": "How to attribute DC Hub: {source, url, license, cite_as, retrieved_at}, or the attribution line as a string."
-}

removedOutput schema / properties / provenance

Removed value: -{
-  "additionalProperties": {},
-  "description": "Source, method, as_of, verification_counts, license, cite_as; quote it when citing.",
-  "properties": {},
-  "type": "object"
-}

removedOutput schema / properties / quota

Removed value: -{
-  "additionalProperties": {},
-  "description": "Caller quota state (remaining calls, tier).",
-  "properties": {},
-  "type": "object"
-}

removedOutput schema / properties / site_evaluation_handoff

Removed value: -{
-  "anyOf": [
-    {
-      "items": {
-        "additionalProperties": {},
-        "properties": {},
-        "type": "object"
-      },
-      "type": "array"
-    },
-    {
-      "additionalProperties": {},
-      "properties": {},
-      "type": "object"
-    }
-  ],
-  "description": "Follow-up calls [{tool, parameters, why}] when the payload carries coordinates."
-}

Changed8 schema fields changedv2.12.43Oct 15, 2026

changedOutput schema / description

Previous value: -"DC Hub envelope: structuredContent mirrors the JSON payload in content[0].text — tool-specific data fields ride at the top level alongside these envelope keys."New value: +"DC Hub envelope: tool data fields ride at the top level beside these keys."

changedOutput schema / properties / _entity / description

Previous value: -"Payload class discriminator (e.g. facility|market|iso_grid|queue_results|deal|report|response) — branch on this before parsing the rest."New value: +"Payload class (facility|market|iso_grid|queue_results|deal|report|response); branch on it."

changedOutput schema / properties / _front_door / description

Previous value: -"In-band front-door hint (first workflow-entry tool of a session): call plan_query(intent) first for the ordered multi-step plan."New value: +"First-tool hint: plan_query(intent) returns the ordered plan."

changedOutput schema / properties / _return_loop / description

Previous value: -"Suggested next-session delta call (get_changes since=24h) so you pull only what changed."New value: +"Next-session delta call (get_changes)."

changedOutput schema / properties / citation / description

Previous value: -"Machine-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."New value: +"How to attribute DC Hub: {source, url, license, cite_as, retrieved_at}, or the attribution line as a string."

changedOutput schema / properties / provenance / description

Previous value: -"Collection-level provenance block: {source, method, as_of, verification_counts, cite_url_template, license, cite_as}. Quote the verification level when citing."New value: +"Source, method, as_of, verification_counts, license, cite_as; quote it when citing."

changedOutput schema / properties / quota / description

Previous value: -"Caller quota state (remaining calls, tier) when available."New value: +"Caller quota state (remaining calls, tier)."

changedOutput schema / properties / site_evaluation_handoff / description

Previous value: -"Pre-built follow-up calls (analyze_site / get_water_risk args) when the payload carries coordinates — an array of {tool, parameters, why} entries."New value: +"Follow-up calls [{tool, parameters, why}] when the payload carries coordinates."

Changed2 schema fields changedAug 30, 2026

removedInput schema / $schema

Removed value: -"http://json-schema.org/draft-07/schema#"

removedOutput schema / $schema

Removed value: -"http://json-schema.org/draft-07/schema#"

Changed5 schema fields changedv2.3.20Aug 14, 2026

removedOutput schema / properties / citation / additionalProperties
```
Removed value: -{}
```

addedOutput schema / properties / citation / anyOf

Added value: +[
+  {
+    "additionalProperties": {},
+    "properties": {},
+    "type": "object"
+  },
+  {
+    "type": "string"
+  }
+]

changedOutput schema / properties / citation / description

Previous value: -"Machine-readable citation: how to attribute DC Hub (dchub.cloud) for this payload."New value: +"Machine-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."

removedOutput schema / properties / citation / properties
```
Removed value: -{}
```
removedOutput schema / properties / citation / type
```
Removed value: -"object"
```

Changed1 schema field changedv2.3.12Jul 28, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "additionalProperties": {},
+  "description": "DC Hub envelope: structuredContent mirrors the JSON payload in content[0].text — tool-specific data fields ride at the top level alongside these envelope keys.",
+  "properties": {
+    "_entity": {
+      "description": "Payload class discriminator (e.g. facility|market|iso_grid|queue_results|deal|report|response) — branch on this before parsing the rest.",
+      "type": "string"
+    },
+    "_front_door": {
+      "additionalProperties": {},
+      "description": "In-band front-door hint (first workflow-entry tool of a session): call plan_query(intent) first for the ordered multi-step plan.",
+      "properties": {},
+      "type": "object"
+    },
+    "_return_loop": {
+      "additionalProperties": {},
+      "description": "Suggested next-session delta call (get_changes since=24h) so you pull only what changed.",
+      "properties": {},
+      "type": "object"
+    },
+    "citation": {
+      "additionalProperties": {},
+      "description": "Machine-readable citation: how to attribute DC Hub (dchub.cloud) for this payload.",
+      "properties": {},
+      "type": "object"
+    },
+    "provenance": {
+      "additionalProperties": {},
+      "description": "Collection-level provenance block: {source, method, as_of, verification_counts, cite_url_template, license, cite_as}. Quote the verification level when citing.",
+      "properties": {},
+      "type": "object"
+    },
+    "quota": {
+      "additionalProperties": {},
+      "description": "Caller quota state (remaining calls, tier) when available.",
+      "properties": {},
+      "type": "object"
+    },
+    "site_evaluation_handoff": {
+      "anyOf": [
+        {
+          "items": {
+            "additionalProperties": {},
+            "properties": {},
+            "type": "object"
+          },
+          "type": "array"
+        },
+        {
+          "additionalProperties": {},
+          "properties": {},
+          "type": "object"
+        }
+      ],
+      "description": "Pre-built follow-up calls (analyze_site / get_water_risk args) when the payload carries coordinates — an array of {tool, parameters, why} entries."
+    }
+  },
+  "type": "object"
+}

Addedv2.3.8Jul 14, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), and the description layers on substantial extra context: the physics model (km x 4.9 µs/km x 2), route_factor 1.4 stamped as inference, confidence_v provenance tiers, dark-fiber screening, and a fail-closed candidate_contract for expired/unknown ids. This is genuinely value-adding behavior disclosure.

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

Conciseness4/5

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

Front-loads the trigger and outcome before diving into the per-pair metrics, and uses a labeled 'CANDIDATE CONTRACT' block for the contract rules. It is dense and slightly repetitive in restating the candidate_id provenance, but nearly every clause carries operational information.

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 4-param, read-only analytical tool with an output schema and full annotation coverage, the description supplies everything an agent needs: trigger, sequencing, the physics/confidence semantics, and the candidate-id contract. Nothing material 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 coverage is 100%, so the baseline is 3, but the description adds real meaning: candidate_ids resolve to FROZEN mint coordinates (zero transposition), cand_ tokens may be mixed into the sites string, and expired/unknown ids are dropped and declared. It also frames max_latency_us against a realistic use case (sync replication 1000-2000 µs).

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?

States a specific verb+resource ('cluster sites by latency') plus the scope (2-8 sites) and the output ('viable low-latency clusters and pairwise RTT floors'). It distinguishes itself from routing work ('deterministic pruning BEFORE detailed routing') and cross-references compare_sites and get_refined_queue, so an agent can place it relative to siblings.

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

Usage Guidelines4/5

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

Gives an explicit trigger ('when the user asks which data center sites can form a low-latency cluster') and a clear ordering rule ('BEFORE any routing work'). It stops short of naming the specific alternative tool to use for the downstream routing step, so it's clear context rather than full when/when-not routing.

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

Deploy Server