cosmetic_correction

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

Annotations already declare readOnlyHint=false and destructiveHint=false, so no contradiction. The description adds valuable context beyond annotations: it operates on calibrated cfa:true frames, is async with per-frame progress, and has an approximate duration. It does not disclose exact side effects on files, but that is partially covered by annotations and the correction nature.

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 sentences with no filler. The key facts — purpose, input state, ordering, async, and timing — are front-loaded and every clause earns its place.

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 9-parameter tool with no output schema, the description covers the key preconditions and timing but omits any indication of return values, output location, or the role of several parameters. It is sufficient to invoke the tool blindly but not to fully understand the operation's result.

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 only 33%, so the description must compensate. It explains the two detection paths (master_dark and auto_detect/hot_sigma) and mentions cfa:true. But parameters like files, out_dir, wait, cold_auto, and hot_dark_level remain unexplained in both schema and description, leaving gaps for a 9-parameter tool.

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 specific verb+resource: 'CosmeticCorrection on calibrated (still mosaiced, cfa:true) frames' with the specific goal of fixing hot pixels via master dark and/or sigma auto-detect. It also distinguishes itself from the debayer sibling by explicitly ordering 'Run BEFORE debayer.'

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: it is for calibrated, still mosaiced frames and must run before debayer. It also notes async behavior and typical runtime. However, it does not state when not to use this tool or name alternative tools beyond the debayer ordering.

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