List cited authorities

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, so the safety profile is covered. The description adds crucial behavioral detail beyond annotations: `treatment` is always null and classifying edges is 'unbuilt work' (with a caution about using a wrong label in a brief), and the tool returns `known_missing` with attestations instead of a 404 for decisions that exist but are not held. This is exactly the kind of nuance an agent needs and is not in the annotations.

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 about 150 words and front-loaded with the core purpose. The treatment paragraph is somewhat lengthy but each sentence adds value (warning against unbuilt classification). The known_missing sentence is crisp. It is structured but not as tight as a two-sentence ideal.

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 adequately explains the return semantics: statute provisions with counts, decisions relied on, treatment always null, and known_missing behavior. It also points to `listCasePassages` for deeper reading. For a read-only citation listing tool, this is sufficient for correct invocation and interpretation.

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 input schema has 100% description coverage for the single `case` parameter, explaining accepted formats (juris doknr, ECLI, or decision URL from `search`). The tool description adds nothing beyond that, so it correctly relies on the schema. 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 ('list') and resource ('outgoing citation edges of one decision'), and breaks down the two citation types: statute provisions with weighted counts (Normenkette) and decisions relied on. It clearly distinguishes from an incoming-citations tool by the phrase 'outgoing', and the detailed content leaves no ambiguity about what is returned.

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 implies usage: it is for a single decision's outgoing citations and is read-only. It explicitly directs to `listCasePassages` when you need to read the actual citing passage, which is a concrete alternative. However, it does not mention `listCitingDecisions` as the counterpart for incoming citations, so it lacks an explicit when-not-to-use statement.

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