Gemini image understanding

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is known. The description adds behavioral context beyond annotations: it explicitly states that the server does not reclassify the source, setting expectations about how the tool handles input types. This is useful transparency that the annotations alone do not convey.

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 two sentences long, front-loaded with the main purpose, and the second sentence clarifies a key behavioral limitation. No unnecessary words or repetition of schema details. Excellent conciseness.

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 a simple tool with rich schema descriptions and annotations, the description covers the essential context: what it does, the input types, and the no-reclassification behavior. It does not describe output format, but no output schema exists and the prompt parameter implies free-form text responses. It is complete enough for an agent to select and 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 provides 100% parameter description coverage, with clear explanations for source, prompt, and mimeType. The tool description itself does not add new parameter semantics, but the schema already does the heavy lifting. Baseline 3 is appropriate here.

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 identifies the tool's purpose: to understand an image from a direct remote URL or local path. It distinguishes from sibling tools by emphasizing that the caller chooses the modality and the server does not reclassify the source. 'Understand' is somewhat generic, but the context of Gemini image understanding and the explicit source scope make it clear.

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 clear usage context by stating 'The caller chooses this modality; the server does not reclassify the source.' This tells the user to use this tool when they have an image source and not to expect auto-detection of non-image inputs. It implicitly differentiates from sibling tools (web, video, audio, document) without naming them explicitly.

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