inpaint_image_pro_flash

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

With no annotations, the description carries the full behavioral burden. It discloses async execution via 'Runs as a background job,' the exact pixel-selection rule, mask purity requirements, alpha handling, and output_method behavior. It leaves the concrete job-result format unspecified, but the behavioral core is well covered.

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 dense but efficiently structured: core behavior first, then constraints, then output modes, then optional inputs, then execution model. Every sentence contributes a distinct, non-redundant fact, and nothing is padded.

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 an 11-parameter tool with nested objects and no output schema, the description covers the essential constraints needed to invoke it correctly: mask semantics, dimension matching, context_image placement, output_method, and background-job execution. The main gap is that it does not describe the job result shape or how to retrieve the finished image, though the sibling get_job_status tool implies that workflow.

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 100%, so the baseline is 3. The description adds useful semantic compression by clarifying that white mask pixels are repainted, alpha is ignored, and output_method distinguishes full composite from changed-pixels-only output. It also reinforces the context_image/bounding_box relationship beyond the schema's bare wording.

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 opens with a specific verb and resource: 'replace only the WHITE pixels of mask_image, preserving unmasked RGBA exactly.' This precisely distinguishes inpainting behavior from generic image editing and from the many sibling image tools. The addition of output_method semantics further disambiguates what the tool returns.

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 operating context: identical dimensions, pure black/white mask, alpha ignored, non-empty mask, optional context_image requiring bounding_box, and background execution. It does not explicitly name alternatives like inpaint, inpaint_v3, or edit_image_pro_flash, but the constraints make the intended use case clear.

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