Analyze a meal image and estimate foods + macros. Pass exactly one of image_url or image_base64. Vision model, capped separately from the text AI budget (free tier 1/mo).
| Name | Required | Description | Default |
|---|---|---|---|
| image_url | No | Public URL of the image. Mutually exclusive with image_base64. | |
| image_base64 | No | Base64-encoded image bytes, no data: prefix. Mutually exclusive with image_url. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description adds the budget cap (free tier 1/mo) and the vision model distinction, which are not in annotations. However, it doesn't disclose potential side effects or output format, but annotations partially cover safety.
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 three short sentences, front-loaded with the core purpose, then input constraints and budget info. Every sentence earns its place.
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 moderately complex tool with no output schema, the description explains what it returns (foods + macros) but lacks details on return format or side effects. Given the clear input schema and annotations, it's adequate but not exhaustive.
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?
The schema already fully documents both parameters with mutual exclusivity descriptions; the description merely restates the oneOf constraint without adding new semantic details.
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 analyzes a meal image and estimates foods and macros, with a specific verb (analyze) and resource (meal image). It distinguishes from sibling ai_parse_meal by explicitly specifying image input and vision model.
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?
It provides clear context for when to use (meal image analysis) and instructs to pass exactly one of image_url or image_base64, but it does not explicitly name alternatives or exclusions relative to siblings.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Most tools have clearly distinct purposes (meals, workouts, routines, body metrics, etc.). A few pairs like get_progress and get_muscle_recovery overlap in data but differ in usage, and the AI tools are separated by input type. Overall, an agent can reliably select the right tool.
Tool names predominantly follow a verb_noun snake_case pattern (get_, log_, update_, delete_, search_, list_). The ai_* prefix is consistent but includes noun-like names (ai_meal_plan, ai_photo_macros) that deviate slightly from verb-first convention. Still predictable and readable.
With 36 tools, the server exceeds the typical 'heavy' threshold, but the scope is broad covering meals, workouts, routines, metrics, AI features, and data sync. Each tool serves a distinct capability, so the count is justified though on the higher end.
The server provides solid lifecycle coverage for core resources: meals (create/read/update/delete), workouts (log/get/delete, set updates), body metrics (get/log with profile upsert), routines (list/get/instantiate), and exercise lookup (search/resolve/list). Minor gaps exist for updating/deleting cardio and water entries, but they are not critical.