mfp_create_meal

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

The description discloses a multi-step behavior beyond the annotations: it stages foods in the diary, saves them via MFP's 'Remember a Meal' flow, clears the scaffolding, and returns the meal_id. It also marks the tool as '[legacy]'. This gives the agent a clear picture of side effects and expected return value, which is significant for a mutating tool with no idempotency.

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 compact and front-loaded with the core purpose, then gives the operational flow in two short sentences. The '[legacy]' tag and returns clause earn their place. There is no filler or repetition of schema details.

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 non-trivial mutation, the description covers the operational mechanism and return value, and annotations give safety hints. It does not mention prerequisites such as needing an existing food_id from mfp_search_food, but the schema already notes that. The main gap is the lack of any caution about the temporary diary staging or the legacy status implications, though these are minor given the behavioral detail already present.

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 description itself does not explain parameters, but the input schema provides detailed descriptions for name, foods, food_id, servings, and response_format. While the context signal claims 0% schema description coverage, the actual schema text contradicts that and appears to cover the parameters well. Since the description adds no parameter-specific value and the schema carries the load, a 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 and resource: 'Create a reusable saved Meal from existing foods.' It clearly conveys that the tool creates a meal rather than logs one, distinguishing it from related tools like mfp_log_meal or mfp_create_custom_food. However, it does not explicitly name or differentiate against siblings, so it stops short of full differentiation.

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 phrase 'reusable saved Meal' implies the tool should be used when the goal is to create a named, reusable meal rather than simply log foods. There is no explicit when-to-use, when-not-to-use, or mention of alternatives such as mfp_log_meal or mfp_create_recipe. Guidance is therefore implied rather than stated.

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