tool_remove_background

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

With no annotations, the description carries the full behavioral burden, but it does disclose a genuinely useful trait: the two-stage pipeline where Gemini paints the subject on a flat chroma-key colour that is then keyed out locally. That explains why key-colour choice matters and hints at failure modes. It still says nothing about file side effects, overwrite behaviour, permission needs, or cost/latency of the model call.

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?

Two sentences, zero filler, with the outcome (transparent PNG) front-loaded and the mechanism following as supporting context. Nothing is restated 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?

With no annotations and no output schema, the description is the only source for behavior and returns; it covers the output format but not where the file lands by default, whether an existing file is overwritten, or that a base64 return is optional. Adequate for a simple single-parameter tool, but thin given the absence of structured support.

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 reported schema coverage for the top-level wrapper is 0%, but the nested parameter object documents every field in detail, so the schema does the heavy lifting. The description contributes mechanism context that motivates key_color's existence, but adds no per-parameter meaning beyond it. A baseline 3 is appropriate.

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 states a specific verb and resource ('Remove the background from an image') and adds the concrete output ('save a transparent PNG'), which is more than a restatement of the name. It does not, however, distinguish this tool from adjacent siblings like tool_edit_image or tool_transform_image, which an agent might reasonably consider for the same request.

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?

There is no when-to-use or when-not-to-use guidance and no mention of alternatives. The agent is left to infer whether this is preferable to tool_edit_image for a masking request, and nothing tells it what conditions make this tool a poor fit (e.g. subjects containing the key colour, though that is buried in the schema).

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