ai_image_editor_create_image

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

With no annotations present, the description carries the full burden and delivers exceptionally. It discloses the async job model (returns id and credits_charged immediately), the exact completion states to poll for (complete, error, canceled), that completed projects include downloads with direct URLs, and that the wait helper returns exact_download_urls separately from expiration metadata. It also warns about the failure modes of hotlinked URLs and prescribes the safer upload flow — precisely the behavioral traits an agent cannot infer from the schema.

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 purpose sentence is front-loaded and the MCP guidance is organized into two scannable bullets. The async-result bullet is tight and information-dense; the file-path bullet is slightly verbose but every clause carries actionable guidance. Given the tool's complexity (async, polling, upload flows), the length is justified.

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 the operational essentials an agent needs: async return semantics, how to obtain results (wait helper or polling), completion states, download URLs, and file-path sourcing. An output schema exists, so return values need not be explained. The only gap is tool-selection context among sibling image tools — the description never explains when this general editor is preferred over specialized siblings.

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 high (86%), so the schema already documents most parameters well. The description adds genuine value for the assets parameter by explaining how to source *_file_path values: prefer an existing Magic Hour file path or the upload-URL endpoint result, and prefer presigned uploads over potentially failing hotlinked URLs. This compensates for the schema's thin coverage of the assets field, which even contains a copy-paste error ('direct URL to the video file').

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 clear verb+resource: 'Edit images with AI.' This correctly conveys that the tool modifies existing images via a prompt rather than generating from scratch, which distinguishes it semantically from ai_image_generator_create_image. However, it does not explicitly differentiate it from the many other image-editing siblings (ai_face_editor_edit_image, photo_colorizer_create_image, etc.), so an agent must infer the general-purpose editing scope.

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 MCP guidance provides strong operational workflow context — how to handle the async job, when to call wait_for_image_project, and when to use the presigned upload flow. What it does not do is state when to choose this tool over the ~13 sibling image tools, and no alternatives are named. Usage is implied by name and schema rather than explicitly routed.

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