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

With no annotations provided, the description carries full behavioral disclosure. It openly states the call returns id and credits_charged immediately, requires waiting for completion, expects statuses like complete/error/canceled, and warns about hotlinked URL failures — strong transparency for a mutation-style async tool.

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 organized with a short headline and two focused MCP guidance bullets. It front-loads the most critical async behavior and keeps the content dense without excessive repetition, though the opening line is somewhat generic.

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 complex async tool with no annotations, the description covers the full lifecycle — initiation, immediate return values, polling/waiting, completion statuses, download URLs, and file input caveats. With an output schema present and detailed parameter schema coverage, this is a complete enough definition, though it could have explicitly noted model-specific limits.

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 already high at 86%, so baseline is 3. The description adds meaningful param-level guidance beyond the schema, particularly around *__file_path values: prefer Magic Hour file paths or upload-returned file_path values, avoid unstable hotlinks, and use the presigned upload flow when in doubt. This is useful semantic context for the assets parameter.

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?

Description states 'Edit images with AI' — a clear verb and resource. It does not, however, explicitly differentiate itself from sibling image-editing/generation tools like ai_image_generator_create_image or ai_face_editor_edit_image, so it is adequately clear but not distinctive.

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 meaningful procedural guidance: it explains that this is an async job, that the agent should call wait_for_image_project or poll the endpoint, and that file paths should come from an upload flow. It does not, however, state when to choose this tool over sibling image tools, leaving usage context implied rather than explicit.

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