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

With no annotations, the description carries the behavioral burden and does well: it discloses non-destructiveness ('Creates a new version on the media doc — the original is preserved') and names the underlying model. It does not mention latency, cost, or rate limits, keeping it below 5.

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?

Four tight sentences, zero redundancy. Purpose comes first, then required inputs, then a behavioral guarantee, then a usage constraint — well front-loaded and highly readable.

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 4-parameter mutation-style tool with no annotations and no output schema, the description covers purpose, inputs, non-destructiveness, and usage limits. It does not explain the return value (a new media version ID would be useful) but is otherwise complete.

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 baseline is 3. The description adds narrative context around mediaId ('the image to edit') and editPrompt ('describing what to change'), and notes the model parameter has a default, which is slightly more than the schema alone provides.

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?

Specific verb+resource: 'Edit an existing image using AI', with the required inputs (media ID + text prompt) named. It clearly distinguishes itself from siblings like generate_image (new image) and edit_video (video editing) by scoping to existing images.

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?

Explicit when-to-use guidance: 'Use sparingly — only when the user explicitly asks to modify an existing image.' This is a strong, actionable exclusion criterion that routes the agent correctly and prevents over-invocation.

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