run_traceflow

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

Annotations provide limited behavioral hints (readOnlyHint=false, destructiveHint=false). The description adds significant context: it injects a synthetic probe, returns hop-by-hop observations, and includes DFW rule hits/drop reasons. No contradiction with annotations.

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 well-structured with a clear summary line and detailed parameter explanations. It is concise overall, though the parameter block could be more compact with a list format.

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?

Despite thorough parameter documentation, the description lacks details on return format, potential errors, prerequisites (e.g., source port must exist), and async behavior. The tool has no output schema, so more guidance on result interpretation would 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?

The input schema has 0% description coverage. The description compensates fully by explaining each parameter's purpose (e.g., 'Source logical port ID (attachment UUID of the VM NIC)'), including defaults for optional ones.

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 action 'Run a Traceflow' and the resource 'trace a packet's path through the NSX overlay', distinguishing it from siblings like get_traceflow_result which retrieves results.

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 implies use for tracing packet paths with details on probe injection and observations. However, it does not explicitly mention when not to use it or direct to sibling tools like get_traceflow_result for results retrieval.

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