WaveGuard

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

With no annotations provided, the description carries the full disclosure burden. It successfully explains the GPU-accelerated computation, the automatic windowing logic, the training/test division (first N windows vs remaining), and the return structure (anomaly scores, confidence, p-values). It could improve by mentioning error conditions, computational constraints, or idempotency.

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 excellently structured: purpose (sentence 1), input requirements (sentence 2), processing logic (sentence 3), outputs (sentence 4), and concrete example (paragraph 2). Every sentence conveys distinct information without redundancy, and critical details are 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?

For a complex ML tool with 4 parameters and no output schema, the description is remarkably complete. It compensates for missing annotations by detailing the algorithmic behavior (overlapping windows, training baseline) and return values. Minor gap: lacks discussion of failure modes or minimum data requirements (though schema enforces minItems: 4).

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%, establishing a baseline of 3. The description adds significant value by explaining how parameters interact algorithmically—specifically how 'data' and 'window_size' determine training windows, and how 'test_windows' relates to the auto-split behavior. The example reinforces parameter semantics effectively.

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 specific verb ('Detect'), clear resource ('anomalies in time-series data'), and distinct methodology ('GPU-accelerated wave physics simulation'). This clearly distinguishes it from siblings like 'waveguard_scan' and 'waveguard_health' by specifying the time-series domain and wave physics approach.

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 provides clear usage context through the concrete example (100 CPU-usage readings) and explains the internal training/test split mechanics. However, it lacks explicit guidance on when to choose this over sibling tools (e.g., 'use this for sequential numeric data vs waveguard_scan for general purposes').

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