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

Annotations already declare destructiveHint=true, idempotentHint=true and readOnlyHint=false, and the description reinforces rather than repeats this: same-name dishes get ingredients replaced under the same id, so the 'destructive' behavior is concretely explained. It also adds genuinely non-obvious traits the annotations cannot carry — all-or-nothing catalog binding, never-estimated values, German-DB-then-USDA resolution order, and what the reply contains.

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 core action and the 'does not log' constraint are front-loaded, and the example in parentheses quickly communicates the input shape. It is dense with useful facts but each sentence carries distinct information; the German term glosses are helpful rather than padding.

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?

With no output schema, the description takes on the job of describing the response (which catalog row each ingredient was bound to) and the failure response (naming the unknown ingredient), which it does. For a two-parameter upsert with atomic behavior, an agent has everything needed to call it correctly and to recover from errors.

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 documents name, grams and foodItemId individually at roughly 50% overall coverage, so the description's main added value is explaining the role of foodItemId as an escape hatch when a name cannot be resolved, and the German-first, specificity-encouraging naming expectation. It doesn't add detail on the grams upper bound or the 60-ingredient cap, but those are already in the schema.

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 ("Saves a recipe as a reusable dish ('Gericht')") and immediately scopes it with "from ingredient names with grams, without logging anything," plus a concrete parenthetical example. That distinguishes it from the sibling logging tools (joiva_log_meal, joiva_log_described_meal) without needing to name them.

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 gives a clear selection rule (use this to build a reusable dish, not to log a consumed meal) and explains the failure path: if a source doesn't know an ingredient nothing is saved, and a more precise name or a foodItemId fixes it. It stops short of naming the alternative sibling tools or stating when to prefer joiva_log_meal outright.

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