image_detect_grid

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

With no annotations, the description carries the full burden, and it does disclose two meaningful traits: the input must already be upscaled, and the tool writes a PNG to disk only when recover_1x_output_path is supplied (a real side effect worth flagging). It omits failure behavior on non-pixel-art input, whether the write overwrites an existing file, and what the detection returns. Adequate but with clear behavioral gaps.

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?

A single tight sentence with the core operation front-loaded and the optional export hedged with 'optionally'. Nothing is wasted and the parenthetical example adds concrete grounding rather than filler.

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?

With no annotations and no output schema, the description should explain what the tool returns (the detected factor? a structure?) and how tolerance affects results. Neither is covered, leaving an agent unable to reason about output shape or parameter tuning for a three-parameter tool. The one thing it does cover — the optional file export — is already documented in the schema.

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 coverage is only 33% and the description adds nothing for the undocumented parameters. 'tolerance' (default 8) — the parameter most likely to be mis-set, since it governs how closely pixel blocks must match — is never explained in the schema or the description. The description only obliquely restates what the schema already says about recover_1x_output_path.

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 names a specific verb ('detects') and resource ('pixel-block factor of an already-upscaled pixel-art image') with a concrete example (4x sprite) and a secondary capability (exporting the 1x native grid). No sibling tool (image_convert, image_stylize_reel, palette_tool, export_spritesheet) overlaps this operation, so an agent can route here unambiguously.

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?

'Already-upscaled' encodes an implicit precondition on the input — the image must be pixel art that was previously scaled — which rules out arbitrary photos or native-resolution art. However, it never states when to prefer this over image_convert or export_spritesheet, nor what to do when detection fails. Usage is implied rather than directed.

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