cpu_next_hops

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

No annotations are provided, so the description carries full burden. It fully discloses read-only nature, the subtle 'fromReady' build-state quirk, hub construction implications (no reach/fee until finished), foreign cells as walls, and the meaning of empty hops. This goes far beyond basic safety to explain genuinely non-obvious behavioral semantics.

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?

Dense but well-structured: purpose first, then mechanics, then planning responsibility, then when-to-use. Every sentence adds value, though the length (5+ sentences) prevents a perfect score. The 'WHEN' marker helps skimmability.

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?

For a complex tool with no output schema and no annotations, the description fully compensates: explains the reach rule formula, candidate facts, walls, hub building, fee behavior, and workflow integration. It covers edge cases (foreign cells, unfinished hubs) and gives actionable planning guidance.

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?

While schema coverage is 100%, the description adds critical meaning beyond field names: it explains that 'towards' is 'a compass, not a route,' clarifies that 'resourceId' determines the exact per-unit transit fee shown, and explains how 'from' being a hub or self-owned affects reach. This transforms dry schema definitions into actionable semantics.

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 opens with a specific verb+resource: "Survey the legal next waypoints from a cell (read-only)." It clearly distinguishes this from siblings like cpu_quote_transport (which quotes transport cost) and cpu_route_network (which plans routes), while precisely defining the one-hop reach rule. This is a textbook example of a purpose that differentiates from alternatives.

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?

Explicitly states when to use: "the cheap point check — call it right before each leg and after cpu_get_changes shows movement," and when to escalate: "replan via cpu_route_network only when a local fix is impossible." This is excellent guidance that maps directly to workflow context.

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