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

Annotations already cover readOnly, idempotent, non-destructive and closed-world, so the description is not burdened with safety disclosure. It still adds real behavioral context beyond them: the deterministic sort order, the fact that 'nothing is blocked' because the entry is 'already computed' with the standard option, and that answering changes something described by 'wirkungText'. It stops short of saying what an empty result means or what answering a question actually mutates.

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 is front-loaded in the first sentence, and the subsequent sentences each earn their place by explaining origin, ordering and return fields. The middle sentence about standard recipes is long and example-heavy ('oil in the dressing, milk or almond drink'), slightly more detail than an agent needs to select the tool, but it is informative rather than redundant.

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?

There is no output schema, so the description carries the full burden of describing returns and does so: each question exposes 'optionen', the preselected 'standard' index, 'wirkungText' and an 'id'. Combined with the explained sort order and the note that nothing is blocked, an agent has enough to call the tool and interpret the result correctly for this low-complexity, single-optional-parameter read 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?

Schema description coverage is 100%, with the single optional 'tz' parameter already documented as an IANA timezone defaulting to Europe/Berlin. The description says nothing about the timezone parameter or its effect on the result set. Baseline 3 applies because the schema fully carries parameter meaning here.

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 resource: open follow-up questions about assumptions made for the user's dishes, and gives concrete examples ('Bullet Proof Coffee', 'warmer Linsensalat') of why such a question exists. It never states the verb 'list' explicitly, but the plural-collection framing and the enumeration of returned fields make the operation unambiguous. It does not explicitly contrast with the obvious counterpart joiva_answer_question, so sibling differentiation is left implicit.

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?

Usage is only implied through context: questions are ordered 'first what a warning of the nutrient assessment depends on, then what its data coverage depends on', which hints the tool belongs in a nutrient-review flow. There is no explicit 'call this when...' statement, no 'do not use this for...' exclusion, and no pointer to joiva_answer_question for resolving the listed items. An agent can infer the scenario but not the trigger.

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