trace_upstream

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

With no annotations provided, the description carries the full burden and does so thoroughly. It discloses that direction is READ rather than guessed, explains the 92.5% connector direction rate and how extractors/generators settle the rest, and states the policy of walking edges BOTH ways when unsure. It also reveals that belts and pipes are traversed but omitted from output, including a concrete node/depth example.

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 organized into three focused paragraphs: purpose/differentiation, direction reliability, and filtering/performance. The cutover narrative adds clarity but is slightly verbose. Every sentence contributes a distinct insight, though the 92.5% statistic and depth example could be trimmed without losing core meaning.

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 annotations and no output schema, the description covers purpose, usage context, directional behavior, and return filtering. It implies a table output and gives a sense of scale ('331 nodes at depth 72'), but it doesn't specify exact output columns or edge cases like cycles or disconnected seeds. Still, it is quite complete for a tool with 5 parameters.

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?

The schema already documents seed, limit, and direction. The description enriches seed with 'one machine or one building type' and elaborates on direction behavior (up/down, BOTH ways fallback). However, save and world are left completely undocumented by both schema and description, and the 60% schema coverage means the description does not fully compensate for those gaps.

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 clear verb+resource: 'What feeds a machine, or what it feeds -- walked on the save's own connections.' It immediately distinguishes this tool from the sibling factory_query, stating that factory_query works between labelled sets while this one targets one machine or building type. The oil extractor/fuel generator example concretely illustrates the intended use.

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 explicitly differentiates from factory_query: 'factory_query answers this between LABELLED sets. This answers it for one machine or one building type.' It also provides a practical cutover scenario, signaling when an agent should prefer this tool. It doesn't explicitly list exclusions, but naming the alternative is strong guidance.

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