graph_trace

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

With no annotations, the description carries full burden. It discloses that the tool reads the cached index, does not read the drawing, and explicitly says it reports if no cache is found. This makes the cache-dependence and failure behavior transparent, which is critical for correct invocation.

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 three sentences, each earning its place: one sentence defines the action and outputs, one gives concrete sample queries, and one provides a critical caveat about stale caches. There is no fluff, and the most important behavior is front-loaded.

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 the tool's complexity (network tracing, cache dependency), the description covers the core behavior, expected outputs, use cases, and limitations. It directs users to rebuild with graph_build if needed, and the output schema already exists for return values. This is complete for correct selection and invocation.

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 description coverage is 0%, so the description must compensate. It mentions 'from a point', which hints that x and y define a location, but it does not explicitly map x/y to that point, nor explain units or coordinate system. This adds some meaning beyond bare numbers but is insufficient for a 0%-coverage schema.

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 clearly states the tool follows the network from a point through the graph_build cache, and lists concrete outputs (curve count, total length, open ends). It also distinguishes itself from the sibling tool graph_build by explicitly mentioning 'Rebuild with graph_build if the drawing changed', making its unique resource and scope unambiguous.

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?

It explicitly answers when to use the tool ('what is downstream of here', 'is this the same run as that') and gives an alternative: 'Rebuild with graph_build if the drawing changed'. This provides clear when-to-use and when-to-avoid guidance, including a named alternative tool.

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