Skip to main content
Glama

DC Hub — Data Center & Power Intelligence

by cloud.dchub

Research Dossier (async)

research_task
Read-onlyIdempotent

Commission an ASYNC, CITED research dossier from DC Hub's corpora (news, deals, facilities, market deep-dive narratives + live market components) — a decision-ready analyst brief with [n] citations, not a lookup. Requires a key (one claim_free_key call), 5 dossiers/day. Submits the question, waits up to ~35s for completion, and returns the finished dossier inline when ready; if still running, returns {task_id} — call research_task task_id= to fetch it. Params: question (required for a new dossier, min 12 chars) OR task_id (poll an earlier one). Typical completion under a minute. Answers "write me a cited brief on this", "what do recent deals say about gas-bridged power". Try: research_task question="What do recent deals say about gas-bridged power for data centers in ERCOT?". Do NOT use for a single fact (use search_intelligence / semantic_search); this synthesizes ACROSS sources with citations.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
task_idNoPoll an earlier submission: the task_id returned by a previous research_task call
questionNoThe research question (min 12 chars) — omit when polling with task_id

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
quotaNoCaller quota state (remaining calls, tier) when available.
_entityNoPayload class discriminator (e.g. facility|market|iso_grid|queue_results|deal|report|response) — branch on this before parsing the rest.
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.
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.
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.

TDQS

A4.3/5.0
Behavior5/5

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

The description richly discloses async behavior: waits up to ~35s, returns inline when ready, returns {task_id} while running, and typical completion under a minute. It also reveals rate limits, key requirements, and citation behavior, all beyond what the readOnly/idempotent/destructive hints already communicate.

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?

The description is dense and mostly earns its length, front-loading the async/cited nature and key constraints. A minor redundancy exists between "waits up to ~35s" and "typical completion under a minute," but overall the structure is efficient for a tool with this much behavioral nuance.

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

Completeness3/5

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

The description covers use cases, exclusions, async behavior, polling, rate limits, and examples—very strong coverage. It is incomplete only because of the task_id/task parameter naming mismatch, which undermines the invocation instructions and makes the description less than fully reliable on its own.

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

Parameters2/5

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

The description explains mutually exclusive modes, the 12-character minimum, and polling semantics. However, it repeatedly refers to the polling parameter as "task_id" while the provided input schema names the property "task". An agent following the description could construct an invalid call, so the semantic guidance is not reliable.

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 description names a specific verb ("Commission"), a concrete resource ("ASYNC, CITED research dossier"), and the intended output ("decision-ready analyst brief with [n] citations"). It explicitly contrasts itself with "a lookup" and points to search_intelligence / semantic_search as alternatives, making it easy to distinguish from sibling tools.

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 when-to-use guidance: quoted question types, a concrete example, and a clear exclusion ("Do NOT use for a single fact") with named alternative tools. It also discloses prerequisites (key, 5 dossiers/day) and the two invocation modes (new question vs polling with task_id).

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 & Power Intelligence 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
Disambiguation4/5

Most tools have clearly distinct purposes despite some thematic overlap, and each description includes explicit 'Do NOT use' guidance to prevent misselection. However, a few pairs like search_intelligence vs semantic_search are nearly identical in function, and the sheer number of tools increases the chance of selecting the wrong one without careful reading.

Naming Consistency4/5

The vast majority of tools follow a predictable 'get_*' prefix for data reads, and many others use verb_noun patterns (analyze_*, rank_*, save_*, set_*). There are a handful of outliers like ai_capacity_index, grid_transition_radar, and site_selection_canvas that break the pattern, but overall the conventions are consistent enough for an agent to infer meaning.

Tool Count2/5

With 82 tools, this server is extremely heavy compared to typical MCP servers (3-15 tools). While the domain is broad, many tools serve narrow sub-purposes and could be consolidated (e.g., multiple site-scoring variants, multiple grid telemetry endpoints). The count overwhelms an agent's ability to choose efficiently and feels like over-fragmentation rather than necessary granularity.

Completeness4/5

The tool surface covers the full lifecycle of data-center siting intelligence: site analysis, grid, fiber, water, climate, tax, permitting, deals, news, saved-site management, and meta-planning. Minor gaps exist (e.g., no delete or update operations for saved sites), but the core workflows are well-supported and the descriptions are comprehensive.

Resources