Skip to main content
Glama

cpu_route_network

Read the world's road network graph of legal waypoints and hops to plan cargo routes, including per-unit transit fees and component connectivity.

Instructions

The road map of the world (read-only): every legal waypoint — your revealed cells and every finished Hub — as graph nodes (owner, hub flag, ready build state, the exact per-unit transit fee for your resourceId cargo, pos, connected-component id) plus every hop the contract would accept as edges (within radius(a)+radius(b)−1 grid steps; default balance: own↔own 1 = adjacent only, own↔hub 3, hub↔hub 5). A Hub counts only once its construction finishes: an unfinished one grants no hub reach and charges no fee, and a foreign one is not a node at all — your own cells stay nodes while they build, just with normal reach (ready: null = nothing built, false = under construction, true = finished). Foreign cells are never nodes: even a single foreign cell between two plain cells is a WALL — only a finished Hub reaches across. Different component ids show exactly that — no chain crosses today, goods stop at the border. Bridging is a strategic decision: a border Hub (it still needs an eligible landing point within reach on the far side), buying land across, or a detour — the sphere is closed, so a wall must encircle to truly seal. Pass from/towards to annotate each node with grid distances (a potential field to reason over). Routing over this map is YOUR job: pick the chain, then verify with cpu_quote_transport. WHEN: the heavy read — plan a journey or a big replan; for point checks while executing use the cheap cpu_next_hops.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
fromNoOptional source cell — annotates every waypoint with its grid distance from here.
towardsNoOptional destination cell — annotates every waypoint with its remaining grid distance.
resourceIdYesThe cargo resource id — every foreign-hub waypoint shows its exact per-unit transit fee for it.
Behavior5/5

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

With no annotations, the description fully carries the burden. It details read-only nature, node conditions (finished hub, own cells vs foreign), component IDs meaning, and edge radius formula. There is no contradiction with annotations as none exist.

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 a single dense paragraph but well front-loaded with purpose. Every sentence adds value, though it could benefit from slight structuring (e.g., bullet points) for easier parsing. Still highly concise for the amount of 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?

No output schema exists, so description must explain return structure. It fully describes nodes (owner, hub flag, ready state, fee, pos, component id) and edges (conditions). Also explains edge case like unfinished hubs. Complete for a complex topology tool.

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 baseline 3. Description adds meaningful context: explains from/towards annotate with grid distances (potential field), resourceId shows per-unit transit fee. This enriches understanding beyond schema.

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 clearly states 'The road map of the world (read-only)' and explains it returns graph nodes and edges. It distinguishes from sibling cpu_next_hops by noting this is for heavy planning versus point checks. The verb 'route' and resource 'network' are specific.

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 states 'WHEN: the heavy read — plan a journey or a big replan; for point checks while executing use the cheap cpu_next_hops.' This provides clear when-to-use and alternative tool, which is exceptional.

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

Install Server

Other Tools

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/sodiqit/project-cpu-mcp'

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