get_traceflow_result

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

Annotations already mark readOnly, idempotent, openWorld, and non-destructive. The description goes further: it discloses the operation_state enum, the observations' structure typed by resource_type, that Dropped* observations include reason and acl_rule_id, and the critical server-side behavior that a completed traceflow is deleted and its id 404s. This is valuable behavioral context beyond the annotations and no output schema exists to carry the load.

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?

Four sentences, every one earns its place: purpose, usage timing, return payload detail, and the surprising 404 lifecycle. It is front-loaded with the verb and resource, then details, then caveat. No filler or repetition of schema content.

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?

Even without an output schema, the description conveys what the agent needs: how to obtain the id (from run_traceflow), what operation states to expect, what fields appear in observations, and how to interpret a 404 for completed traceflows. For a simple read-poll tool with rich annotations, nothing essential is missing.

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 100%: traceflow_id is already described as 'Traceflow ID from a previous run_traceflow call' and target as 'Optional NSX Manager target from config'. The description adds no param-specific detail beyond this, so the baseline 3 applies. No parameter is left unexplained by the 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?

States a specific verb ('Get'), a clear resource ('existing Traceflow'), and the result ('current state and observations'). It is instantly distinguishable from siblings like run_traceflow, which starts a traceflow, and list/get policy tools, which operate on unrelated resources. The [READ] prefix reinforces the read nature.

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 instructs 'Use this to check a previously initiated traceflow without waiting', which defines the exact moment an agent should call it. The lifecycle note about completed traceflows being deleted server-side and 404ing prevents an agent from misinterpreting a 404 as an error, and implicitly tells it not to use this tool to start traceflows.

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