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

Annotations already mark the tool as non-read-only, open-world, non-idempotent, and non-destructive. The description adds substantial behavioral context beyond annotations: billing comes from the Gisoo credit, USD cost appears in the text, the default model and resolution are named, and text rendering is disclosed as unreliable.

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 definition is front-loaded with the core action and return format, then adds cost, model, and rendering caveats. The final Persian sentence duplicates information already provided in English, which is slightly redundant but not harmful.

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?

The description covers purpose, return format, default parameters, cost model, billing source, model alternatives, and a key image-text limitation. With no output schema, it still clearly tells the agent what the tool returns and what tradeoffs to expect.

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 description coverage is already 100%, so the baseline is 3. The description adds useful semantics beyond the schema by naming the default model and resolution, explaining that larger sizes and higher quality cost more, and pointing to list_models for model selection.

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: "Create one image from a text description" and specifies the return format as an MCP image in base64. This clearly distinguishes generate_image from sibling tools such as create_video, generate_music, and text_to_speech.

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?

It explains the default model as quick and inexpensive and directs the agent to list_models when higher quality is needed. It also gives a practical usage caveat: leave text out of the image and add it later, especially for Persian. It does not explicitly compare against every non-image sibling, but the resource-specific guidance is strong.

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