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

With no annotations provided, the description fully bears the weight of behavioral disclosure. It clearly states the async nature, immediate return of id and credits_charged, the required follow-up to retrieve results, and the pitfall that hotlinked URLs can fail. This goes well beyond a simple 'create' statement and prepares the agent for the operation's real-world behavior.

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 well-structured: it front-loads the core purpose and cost, then provides targeted MCP guidance in two bullets. The file-path instruction is verbose but essential and directly actionable. There is no filler, and the flow from purpose to async handling to input requirements is logical.

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?

Given the async workflow and the presence of sibling wait_for_image_project, the description adequately covers the complete call sequence: initiate, receive id, wait/poll, and retrieve downloads. It addresses the likely error sources (URL stability) and credits. It does not detail the output schema, but that is covered separately, and it omits any rate-limit or retry information, which are minor for this tool.

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?

While the schema already documents name, style, and assets with good coverage (67%), the description enriches the most critical parameter, assets.image_file_path, by explaining the preferred input methods (Magic Hour file paths or upload-URL file_path) and warning about unreliable hotlinked URLs. This adds practical meaning that the schema hints at but doesn't fully convey. Other parameters (name, style) are straightforward and need no extra explanation.

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 opens with 'Create an AI headshot,' a clear verb+resource statement that exactly matches the tool name and differentiates it from image editing, swapping, and other generation tools. It also specifies the cost and confirms the resource type, leaving no ambiguity about what the tool does.

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 strong post-invocation guidance: it explains that the job is async and directs the agent to call wait_for_image_project or poll the endpoint. However, it never explicitly states when to use this tool versus alternative generators (e.g., face swap or clothes changer). The intended usage is implied by the name and purpose but not directly contrasted with siblings, so exclusions are missing.

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