cpu_route_network

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

With no annotations, the description carries full burden. It clearly states the tool is read-only, explains the graph structure (nodes as waypoints, edges as hops), and covers key behaviors: foreign cells excluded, component ids show connectivity, and the effect of from/towards parameters. It does not detail performance or error cases, but the 'heavy read' label provides some behavioral insight. Overall, it is transparent beyond the bare minimum.

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

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

The description is quite long and includes many details (component ids, strategic bridging, sphere closure) that, while relevant, could be condensed. It starts with the main purpose but becomes verbose. Structure is logical but not succinct. Score reflects average conciseness.

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

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

Given no output schema and no annotations, the description covers the tool's functionality thoroughly: what the output contains (nodes with attributes, edges with distance rules), exceptions (foreign cells are walls), and usage context (heavy read for planning vs. lightweight check). It provides enough context for an agent to decide when and how to use the tool, though an example output format would further improve completeness.

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

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

Schema coverage is 100%, so baseline is 3. The description adds by explaining that from/towards 'annotate each node with grid distances (a potential field to reason over),' which provides strategic context beyond the schema's 'Optional source cell.' This extra meaning justifies a higher score.

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

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

The description explicitly states 'The road map of the world (read-only): every legal waypoint... plus every hop' and further clarifies its use for planning heavy reads, distinguishing it from sibling tools like cpu_next_hops (cheap point checks) and cpu_quote_transport (verify route). The verb 'route' implies network exploration, and the resource is clearly the network graph.

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

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

The description provides explicit WHEN guidance: 'the heavy read — plan a journey or a big replan; for point checks while executing use the cheap cpu_next_hops.' It also implies when not to use (for point checks) and names an alternative tool (cpu_next_hops). This meets the highest standard for usage guidance.

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