denoise

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

It adds context about algorithm fallback behavior and the checkpoint-before-running step, which complements the destructiveHint annotation. But it does not disclose that the tool likely modifies the active image, what the operation produces, or the full impact of the checkpoint behavior.

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?

Two terse sentences convey the key algorithm-selection logic and a critical safety instruction with no filler. Every clause carries information, and the most important behavioral detail 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?

The description is too cryptic for a destructive, 7-parameter tool with a nested params object and no output schema. It omits the target of the operation, the conditions for using denoise versus its many siblings, and the post-operation state, leaving substantial gaps for an agent to fill.

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 description adds meaning to the strength and NXT-specific parameters by linking them to linear/non-linear algorithm selection. It does not explain the id, params object, or checkpoint parameter beyond the schema's own descriptions, and with only 57% schema coverage, this is only partial compensation.

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 identifies specific denoising processes (NoiseXTerminator, MultiscaleLinearTransform, TGVDenoise) and a strength range, so an agent can infer the tool's purpose. It does not explicitly state 'denoise the active image' or differentiate from sibling processing tools, leaving some ambiguity.

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 gives explicit internal selection rules: use NXT if installed, else MLT for linear data or TGV for non-linear, plus a 'checkpoints first' instruction. However, it does not explain when to choose denoise over sibling tools like deconvolve or blur, nor when it should not be used.

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