Skip to main content
Glama

cpu_route_network

Plan a shipment by exporting the route graph for one move to a JSON file; receive file path, connectivity, hop counts, instructions, and a prefilled quote call to verify your chain.

Instructions

Export the route graph for ONE move you are planning (read-only, needs from, towards, resourceId and amount). It does NOT answer with the graph: it writes the graph to a uniquely named JSON file in the temporary directory and answers with the file path, the schema and snapshot versions, node and hop counts, whether the two ends are connected, ordered instructions, and a prefilled cpu_quote_transport call. Load the file with code and plan over it — never paste it into the conversation. USE IT WHEN you have a code runner; without one, plan leg by leg with the cheap cpu_next_hops instead. Both ends must be your own cells past their first completed reveal — a foreign Hub is passage, never an end of a shipment. Nodes are every cell a shipment may pass through: Virgin ground (no completed reveal, minted or not, owner null when nobody has minted it), your own cells, and any cell with a finished Hub, foreign ones included; only foreign land past its first reveal without a finished Hub is closed, and a belt of it wider than your reach is the WALL. Each node carries owner, Virgin/own/finished-Hub flags, its own reach radius and the exact per-unit transit fee for your cargo. Edges are the hops the contract accepts (radius(a)+radius(b)−1 grid steps, so a finished Hub tier reaches as far as its own catalog row serves). Only the component(s) your two ends sit in are exported; connected: false means no chain exists today — goods stop at the border until you bridge it with a border Hub (it still needs an eligible landing point within reach on the far side), land across, or a detour. Routing over the graph is YOUR job: pick the chain, then verify it with cpu_quote_transport before spending. Pass lotId to plan one lot’s way home instead: for an Evicted lot the source becomes the hub it was listed on, admitted from the lot itself at the reach and the rate recorded there, so the plan holds after that hub is demolished, rebuilt, left unfinished or sold. Only the source changes — the destination is still your own revealed cell, every later waypoint keeps the ordinary rules, and the prefilled quote call becomes cpu_quote_lot_return.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
fromYesSource cell tokenId — where the cargo stands now. Must be your own cell past its first completed reveal; a foreign Hub is passage, never an end of a shipment.
lotIdNoOptional lot id — plan the way home for this lot instead of an ordinary shipment. For an Evicted lot the source is the hub it was listed on, admitted from the lot itself with the reach and the rate recorded there, so the plan survives that hub being demolished, rebuilt or sold. Nothing after the source changes: the destination is still your own revealed cell and every waypoint follows the ordinary rules. Verify the chain with cpu_quote_lot_return.
amountYesUnits to move, as a positive integer string (matches on-map resource balances). Carried through the graph and into the prefilled quote call unchanged.
towardsYesTarget cell tokenId — where the cargo must end up. Must be your own cell past its first completed reveal, and a different cell from `from`.
resourceIdYesThe cargo resource id — every foreign-Hub node carries its exact per-unit transit fee for it.

Schema Changelog

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

  1. Changed16 schema fields changedv0.10.0
    • addedInput schema / properties / amount
      Added value: +{
      +  "description": "Units to move, as a positive integer string (matches on-map resource balances). Carried through the graph and into the prefilled quote call unchanged.",
      +  "pattern": "^[1-9]\\d*$",
      +  "type": "string"
      +}
    • removedInput schema / properties / from / anyOf
      Removed value: -[
      -  {
      -    "maximum": 48990,
      -    "minimum": 1,
      -    "type": "integer"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]
    • removedInput schema / properties / from / default
      Removed value: -null
    • changedInput schema / properties / from / description
      Previous value: -"Optional source cell — annotates every waypoint with its grid distance from here."New value: +"Source cell tokenId — where the cargo stands now. Must be your own cell past its first completed reveal; a foreign Hub is passage, never an end of a shipment."
    • addedInput schema / properties / from / maximum
      Added value: +29150
    • addedInput schema / properties / from / minimum
      Added value: +1
    • addedInput schema / properties / from / type
      Added value: +"integer"
    • addedInput schema / properties / lotId
      Added value: +{
      +  "anyOf": [
      +    {
      +      "pattern": "^\\d+$",
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "description": "Optional lot id — plan the way home for this lot instead of an ordinary shipment. For an Evicted lot the source is the hub it was listed on, admitted from the lot itself with the reach and the rate recorded there, so the plan survives that hub being demolished, rebuilt or sold. Nothing after the source changes: the destination is still your own revealed cell and every waypoint follows the ordinary rules. Verify the chain with cpu_quote_lot_return."
      +}
    • changedInput schema / properties / resourceId / description
      Previous value: -"The cargo resource id — every foreign-hub waypoint shows its exact per-unit transit fee for it."New value: +"The cargo resource id — every foreign-Hub node carries its exact per-unit transit fee for it."
    • removedInput schema / properties / towards / anyOf
      Removed value: -[
      -  {
      -    "$ref": "#/properties/from/anyOf/0"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]
    • removedInput schema / properties / towards / default
      Removed value: -null
    • changedInput schema / properties / towards / description
      Previous value: -"Optional destination cell — annotates every waypoint with its remaining grid distance."New value: +"Target cell tokenId — where the cargo must end up. Must be your own cell past its first completed reveal, and a different cell from `from`."
    • addedInput schema / properties / towards / maximum
      Added value: +29150
    • addedInput schema / properties / towards / minimum
      Added value: +1
    • addedInput schema / properties / towards / type
      Added value: +"integer"
    • changedInput schema / required
      Previous value: -[
      -  "resourceId"
      -]New value: +[
      +  "from",
      +  "towards",
      +  "resourceId",
      +  "amount"
      +]
  2. First observedv0.8.0

TDQS

A4.8/5.0
Behavior5/5

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

No annotations exist, so the description carries the full disclosure burden and it delivers: the read-only nature, the temp-file side effect with 'never paste it into the conversation,' the component-scoped export, the `connected: false` semantics, the node/edge model including the WALL definition, and the transfer of routing responsibility to the caller. The lotId paragraph even discloses how the plan survives hub demolition, rebuild or sale. Nothing about the tool's behavior is left to inference.

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-loaded and logically sequenced: purpose, output behavior, usage condition, domain model, failure semantics, responsibility boundary, lotId special case. It is long (roughly 380 words) and repeats some constraints already in the schema (foreign Hub never an end, lotId eviction behavior), but the information density is high and the complexity of the contract model justifies the length.

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 no annotations and no output schema, the description is remarkably complete: it enumerates the return payload (file path, schema/snapshot versions, node/hop counts, connectivity, ordered instructions, prefilled quote call), defines every domain term (Virgin ground, finished Hub, WALL, reach), states failure semantics, and mandates the follow-up verification step. An agent can decide, invoke, and interpret the result with no external documentation.

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% with unusually detailed per-parameter descriptions (from/towards constraints, amount as positive integer string carried through unchanged, lotId's eviction semantics), so the baseline is 3. The description adds the conceptual model on top — node composition, reach-radius edge formula, per-unit transit fee per resourceId, and the WALL — which deepens the meaning of from/towards/resourceId, though it is contextual rather than new per-parameter mechanics.

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?

Leads with a specific verb+resource: 'Export the route graph for ONE move you are planning' and pins scope with 'read-only' and the four required params. It disambiguates from siblings by stating what it is not ('It does NOT answer with the graph: it writes the graph to a uniquely named JSON file') and by contrasting with the cheap cpu_next_hops alternative. No ambiguity about what this tool produces or how it differs from nearby 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?

Explicitly conditional: 'USE IT WHEN you have a code runner; without one, plan leg by leg with the cheap cpu_next_hops instead.' It names the alternative tool, gives the adoption condition, prescribes the post-call workflow (load file, plan over it, verify with cpu_quote_transport before spending), and covers the lotId branch pointing to cpu_quote_lot_return. This is textbook when-to-use guidance.

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

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/projectcpu/project-cpu-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server