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

Annotations indicate readOnlyHint=false and idempotentHint=false, which align with the write behavior. The description adds context that saves a 'child generation result' and is 'App-only,' clarifying the data model and invocation scope. It could mention return behavior, but annotations cover safety traits adequately.

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 tightly worded sentences immediately establish the tool's restricted audience and purpose. No wasted words; every element contributes essential context.

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 tool intentionally hidden from host LLMs, the description provides sufficient context for an agent to recognize it as internal. Schema covers required parameters, and the description clarifies the triggering flow. Minor gap: no return value or error behavior described, but given the 'App-only' designation, this is less critical.

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 covers all 5 parameters with descriptions, so baseline is 3. The description doesn't add new parameter-level information beyond what's in the schema, though it gives context for image_base64 and parent_generation_result_id through 'user-edited image' and 'child generation result.'

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 states the tool's function: 'save a user-edited image from the shared ImageDetail retouch editor as a child generation result.' It uses a specific verb and resource, and the 'child generation result' distinguishes it from sibling save tools like save_generated_avatar.

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?

Explicitly states when to use: 'after the user presses Save.' Also clearly excludes host LLMs with 'Hidden from host LLMs; the MCP iframe calls this,' providing strong context for invocation.

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