Skip to main content
Glama

get_celestia_hardware_usage

What the Celestia nodes that Unity Nodes runs actually use, measured on its own servers and shown beside Celestia's recommended hardware, from Unity Nodes Pulse: CPU cores (median, 95th percentile and maximum), RAM of the processes, network and disk I/O (median and 95th percentile; the disk I/O says how many hours of samples it rests on when that is less than the node has), the data size with its change per day and its growth carried forward (per day, in 90 days, when the disk would fill), an estimate of the network traffic per month, and for the Fibre service how full its shard store is against its budget and how many shards it uploaded and served in the window (successful and failed apart), for each node role that has a node (validator, consensus node, bridge, Fibre, light node, Fibre included on mainnet and on Mocha), each node named by its role and CPU, over 1, 7 or 30 days. Measured values, with clearly labelled estimates kept apart from them (the Celestia Foundation's Fibre calculator for Unity Nodes' voting power and, on mainnet, Celestia's own planning scenario for bridge data): the chain's own load in the same window (block data per second at the median, 95th percentile and maximum) beside the block limit read from the chain, the average block time and how much of that capacity the load fills, with a correlation r of each node's CPU, network and disk load with it (a link in how they moved, not a cause; only loads with a link are listed, and it is shown once four hours overlap), and the answer says how much of the window the samples fill (the fewest samples of any node times the step, with a gap or a late start in the data named), so early figures are provisional. For what Celestia's documentation requires, use search or get_doc ("Hardware requirements"); for servers that meet it, list_datacenter_offers; for an estimate of Fibre load, size_fibre_node. Celestia only.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "get_celestia_hardware_usage"
  }
}

Input Schema

NameRequiredDescriptionDefault
roleNoOnly this node role; all roles when left out
windowNo1d, 7d or 30d: the span the median, 95th percentile and maximum cover7d
networkNomainnet or the Mocha testnetmainnet

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.8/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does substantial work: it separates measured values from labelled estimates, discloses sample-coverage/provisional-figure caveats (fewest samples times step, gaps, late starts), and explains that correlations are links not causes shown only after four hours of overlap. Auth, rate limits, and error behavior remain undisclosed, keeping it from a 5.

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

Conciseness2/5

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

The definition is essentially one enormous run-on sentence that dumps return-field enumerations into the description. The core purpose is front-loaded, but the wall of nested clauses (percentiles, sample coverage, Fibre shard budget, correlation caveats) is hard to scan and would benefit from structure or deferral to an output schema.

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?

There is no output schema, so the description must explain the return values, and it does so comprehensively — metrics, percentiles, per-role breakdowns, estimates versus measurements, coverage caveats. For a complex read-only analytics tool, an agent has enough to interpret results correctly.

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

Parameters3/5

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

Schema coverage is 100% and all three parameters are enum-described, so the schema does the heavy lifting. The description reinforces the window options (1, 7, 30 days), roles (validator, consensus, bridge, Fibre, light), and mainnet/Mocha distinction, but adds no syntax or semantic detail beyond the schema. Baseline 3 applies.

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

Purpose4/5

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

The opening states a specific verb and resource (hardware the Unity Nodes Celestia nodes actually use, shown against recommended hardware) and the closing routes to distinct siblings (search/get_doc for documentation, list_datacenter_offers for servers, size_fibre_node for Fibre load). The core purpose is clear, but it is buried inside a very long run-on clause, so the agent must parse a lot to extract it.

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?

The final sentences give explicit alternative routing: use search or get_doc for documentation-required hardware, list_datacenter_offers for servers that meet it, size_fibre_node for an estimate of Fibre load. What's missing is when NOT to use this tool or which sibling supersedes it for overlapping hardware questions.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources