Generate or edit images (Multi-Model: Flash & Pro)

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

The description adds valuable behavioral context beyond annotations. While annotations indicate readOnlyHint=true and openWorldHint=true, the description explains practical behaviors: automatic mode detection, local filesystem reading to avoid token usage, and return formats (MCP image content blocks and structured JSON with metadata). It doesn't contradict annotations and provides operational insights not covered by structured fields.

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 well-structured and appropriately sized. It starts with a clear purpose statement, then lists usage modes in a bullet-like format, and ends with operational details. Every sentence adds value, though the final sentence about return formats could be slightly more concise. Overall, it's efficient and front-loaded with essential information.

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 tool's complexity (14 parameters, multiple modes) and rich schema coverage (100%), the description provides good contextual completeness. It explains usage modes, behavioral traits, and output formats, compensating for the lack of an output schema. However, it could briefly mention limitations or error cases to achieve a perfect score, but it's largely sufficient for an agent to use the tool effectively.

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?

With 100% schema description coverage, the schema already documents all 14 parameters thoroughly. The description adds minimal parameter semantics beyond the schema, mainly by grouping parameters into usage modes (e.g., input_image_path_* for multi-image conditioning). This meets the baseline of 3 since the schema does the heavy lifting, but the description doesn't significantly enhance parameter understanding.

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: 'Generate new images or edit existing images using natural language instructions.' It specifies the verb ('generate or edit'), resource ('images'), and distinguishes from siblings like 'upload_file' and 'maintenance' by focusing on image creation/modification rather than file management or system operations.

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 provides explicit usage guidance by detailing four distinct input modes (pure generation, multi-image conditioning, File ID editing, File path editing) and explaining how the tool automatically detects mode based on parameters. It also distinguishes from sibling tools by not overlapping with their functions (e.g., 'upload_file' is for uploading, while this tool uses uploaded or local files).

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