List case passages

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, so the safety profile is covered. The description adds substantial behavioral context beyond that: rn is read from the court's own markup and never inferred, anchor_basis values and when pin-citing is safe, amtliche_seite is always null because texts carry no page breaks, pagination appears only when there is more than one page, and around returns not_in_corpus rather than silently returning a different passage. This is rich, honest behavioral disclosure.

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 longer than average but every section earns its place: the opening sentence states the core purpose, the rn/anchor_basis paragraph prevents citation misuse, the amtliche_seite paragraph prevents a false expectation, and the SIZE/around paragraphs give operational guidance. It is front-loaded with the most important facts. Slight redundancy in the around paragraph (repeats the centred-window idea) keeps it from a 5.

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 read-only list tool with 4 parameters, no output schema, and no nested objects, the description covers everything an agent needs: what the tool returns, how to identify the case, how to page, how to cite safely, and what to expect when a number is absent. The absence of an output schema raises the burden, and the description meets it by describing the return shape (paragraphs with permalinks, rn, anchor_basis, amtliche_seite, pagination).

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 50%: the schema documents `case` and `around` but not `limit` or `offset`. The description compensates by explaining limit's max (400, enough for a whole decision), offset's role in paging, and around's semantics (centred window, takes a printed number, not combinable with offset). It adds meaning beyond the schema, though it doesn't spell out offset's default or exact paging math, which the schema already provides.

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 opens with a precise statement: 'The full text of one decision, split into its paragraphs, each with a permalink you can cite.' This clearly identifies the resource (case passages), the action (list), and the distinguishing output (paragraphs with permalinks). It also differentiates from siblings like listCitingDecisions and listCitedAuthorities by focusing on the decision's own text rather than citation relationships.

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 gives explicit when-to-use guidance: 'the right call when listCitingDecisions gave you a citing_rn, when a search hit came back anchored at …#rd_51, or when you want the passage around a pin cite and not the whole judgment.' It also explains when not to use it (when you want the whole judgment, use limit; when you want a specific page, you can't because amtliche_seite is null). It names the alternative navigation methods (offset, limit, around) and their trade-offs.

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