save_image_fills

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

The description adds substantial behavioral context beyond the readOnlyHint annotation: it explains that images are deduplicated by imageHash, files are written to disk, path can be null, mixed indicates per-text-range fills, and format is sniffed. These details are not available in annotations, making the description highly transparent.

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?

The description is long but every sentence earns its place: it front-loads the primary purpose and differentiator, then systematically explains the return shape, field meanings, deduplication, edge cases, and alternatives. It is well-organized and free of fluff, making it appropriately concise for its complexity.

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?

Given the rich return type and no output schema, the description fully compensates by detailing the output structure, field semantics, deduplication behavior, and edge cases. It also covers when to use alternatives, providing complete context for an agent to invoke the tool correctly.

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 input schema already provides full descriptions for both parameters (outDir and nodeIds) with 100% coverage. The tool description does not add new meaning to the parameters themselves; it only restates 'write to disk under outDir' which mirrors the schema. No baseline adjustment is warranted, so a neutral 3 applies.

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 clearly states the tool's purpose with a specific verb and resource: 'Extract the ORIGINAL image bytes behind each node's IMAGE fills and write them to disk.' It also distinguishes itself from sibling tools by contrasting with save_screenshots/get_screenshot and export_pdf, making its scope unambiguous.

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?

Explicit guidance is provided on when to use this tool versus alternatives: 'unlike save_screenshots / get_screenshot which re-render the composited node' and 'For a rendered/composited raster use save_screenshots; for a vector node use export_pdf.' This makes the decision process clear.

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