edgegate_predict_npu_coverage

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

With no annotations provided, the description carries the full burden of disclosing behavior. It honestly states this is heuristic ('Heuristic — the real device run remains authoritative'), explains what makes the coverage percentage 'latency-honest' (compute-weighted), and enumerates the return items. It could additionally state that this tool itself does not spend credits, but the 'BEFORE spending' context implies it, and no side effects are expected for a prediction function.

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 two sentences, front-loaded with the core purpose and timing, followed by a compact list of return values and an important caveat. Every sentence earns its place with substantive information, and there is no filler or repetition.

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?

The description provides a solid overview of what the tool does and what it returns, which is crucial since no output schema exists. It is missing parameter-level semantics and explicit cost behavior, but the tool's scope is simple (two standard IDs) and the output list is specified, making it reasonably complete for an agent to invoke correctly.

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, and the description does not mention 'workspace_id' or 'artifact_id' at all. It fails to clarify that the artifact should be an ONNX model or how the workspace/artifact relationship matters, leaving the agent to guess the meaning of these parameters beyond their names.

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 a specific verb ('Predict') and resource ('which ONNX ops will run on the Qualcomm Hexagon NPU vs fall back to CPU'), and adds the timing context ('BEFORE spending any AI Hub credits'). It distinguishes itself from sibling tools by focusing on pre-investment prediction rather than execution or reporting.

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 phrase 'BEFORE spending any AI Hub credits' provides a clear when-to-use context, implying this tool should be used before committing compute resources. It does not explicitly name alternatives or state when not to use it, but the heuristic disclaimer and reference to 'the real device run' clarify that other tools are needed for authoritative results.

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