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

With no annotations provided, the description carries the full burden, and it delivers: it discloses the async job behavior, immediate return of id and credits_charged, how to obtain the finished result via the wait helper or polling until complete/error/canceled status, and that completed projects include downloads with direct URLs. It even notes the exact_download_urls distinction. This is thorough, accurate behavioral disclosure.

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 statement is front-loaded in one concise sentence, followed by a well-organized MCP guidance block covering the async workflow. The guidance is earned content given the job-based nature of the tool. Minor inefficiency: it describes both the wait helper and the raw polling GET endpoint, where the wait helper alone would suffice for most agents.

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 output schema covers return values and the input schema covers all 6 parameters at 100% coverage, so the description only needs to convey the workflow — which it does completely. It tells the agent the job is async, what comes back immediately, how to wait for completion, the possible terminal statuses, and where download URLs live. Nothing essential is missing for correct invocation.

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 100%, so the baseline is 3. The description itself adds minimal parameter-level meaning beyond the schema, but the schema already documents each parameter richly (model enum with costs/resolutions/tiers, resolution per-model support, style tool enum). The description's mention of id and credits_charged adds return-context rather than parameter semantics. Baseline 3 is appropriate.

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+resource ('Create an AI image') and adds 'advanced model selection and quality controls' which clearly distinguishes this general-purpose generator from the many specialized siblings (ai_clothes_changer, ai_face_editor, ai_headshot_generator, etc.). An agent can immediately tell this is the general/advanced tool rather than a niche one.

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 gives solid workflow guidance: it explicitly says this starts an async job, returns id plus credits_charged immediately, and tells the agent to call wait_for_image_project or poll the GET endpoint for completion. However, it does not explicitly state when to use this tool versus the many sibling image generators (when-not/alternatives routing is only implied by 'advanced model selection'). The async guidance is present but the sibling differentiation is absent.

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