Gemini image generation

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

With no annotations, the description carries the full burden and does well: it discloses the output format/location, that exactly one image is produced, that quota is consumed, and a hard content-policy limit. It omits failure modes, whether existing files are overwritten, and any latency behaviour.

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?

Three tight sentences: capability first, then output location/format, then the content restriction. Nothing is repeated and no sentence is padding.

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?

No output schema exists, and the description compensates by stating the return value is the file path, along with where the file lands and in what format. Gaps remain around quota-exhaustion behaviour and error responses for a tool with no annotations to fall back on.

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 prompt, filename, and aspect are already documented in the schema. The description only adds the concrete <date>-<slug>.<ext> naming convention and typical 1024×1024 JPEG output, leaving the aspect hint semantics entirely to the schema.

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?

States a specific verb and resource ("Generate one image with Gemini") plus the downstream effect: saved to a named directory as <date>-<slug>.<ext> and returned as a path. That clearly separates it from the text-oriented siblings gemini_ask and gemini_research.

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?

Gives real usage context: it consumes Google AI Pro quota, produces exactly one image per call, and is restricted to personal content ("never work code, client or customer data"). It never explicitly routes the agent to a sibling for text/research tasks, so alternatives are left implicit.

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