apply_convolution

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

No annotations provided, so description carries burden. It indicates the operation modifies the file ('Aseprite file to modify'), explains optional region scoping (width>0 & height>0), and parameter defaults. Lacks explicit statement about in-place modification but is clear enough.

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?

Concise intro followed by structured argument list. Every sentence adds value, though the description could be more front-loaded with the verb. No unnecessary words.

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?

Covers all parameters with sufficient context, including reference to list_convolution_matrices for matrix names. Does not mention output (no output schema), but for an in-place modification tool this is acceptable.

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 0%, but description adds meaning for all 8 parameters: filename (file to modify), matrix (built-in name), layer_name (default active), frame_index (1-based), region parameters with condition. Adds significant value beyond schema titles.

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?

Clearly states it is a 'Native convolution filter' for blur, sharpen, edge, emboss, etc. Differentiates from sibling filters like adjust_brightness_contrast by focusing on convolution matrices.

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?

Describes parameters but does not explicitly state when to use this tool vs alternative filters. Mentions that matrix names come from list_convolution_matrices, but no when-not or alternative guidance.

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