deconvolve

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

Annotations already mark the tool destructive and non-readonly, and the description adds substantial behavioral context: it is async-ish, can take minutes, checkpoints first, deringing is on, and dark-ring artifacts should be inspected afterward. Nothing in the description contradicts the 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?

Three dense sentences: implementation selection, post-check advice, and execution behavior. Every sentence carries useful information with 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 covers algorithm, fallback, safety, artifact checking, and timing, which is strong for a mutating async tool. But with no output schema and an 'async-ish' promise, it does not specify what the tool returns, how to monitor completion, or whether it modifies the image in place; the agent must infer these from sibling job/status tools.

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?

With schema coverage at only 18%, the description partially compensates by connecting fwhm_px to measured FWHM, clarifying correct_only mode, and describing the BXT/native fallback relevant to method. However, most parameters—iterations, adjust_halos, sharpen_stars, sharpen_nonstellar, and deringing_dark—receive no semantic explanation in either the schema or the description.

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 states a concrete operation—deconvolution—and goes beyond the name by specifying exact implementation details: BlurXTerminator when available, otherwise native Richardson-Lucy with a PSF derived from measured FWHM. This is specific enough to distinguish it from sibling sharpening/blurring tools.

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 clear context for choosing the internal mode (BXT if installed, native fallback) and targeted workflow advice such as using correct_only for the linear stage and checking crop_preview for dark rings. It stops short of explicitly saying when to prefer deconvolve over sharpen or other alternatives, so it is not a full when/when-not guide.

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