Find cases citing a judgment

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

Annotations already cover read-only, idempotent, open-world, and non-destructive behavior. The description adds context beyond those: it reveals the data source (CELLAR), the relationship type (work_cites_work), and the guarantee that results are based on authoritative citations, not keyword co-occurrence. This enriches the agent's understanding of how the tool behaves without contradicting the annotations. It does not, however, describe output format or pagination, but that is partially covered by the output schema.

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 a single sentence that front-loads the tool's core purpose ('Find citing judgments') and immediately adds distinguishing context. It contains no filler, does not repeat annotations, and every clause adds value: the mechanism ('authoritative CELLAR work_cites_work relationships') and the exclusion ('never keyword co-occurrence'). This is an exemplary concise structure.

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?

Despite having an output schema, the description is insufficient for a tool with 6 parameters and only 1 required. It fails to explain how to specify the target case (identifier format?), what the court filter enumerates, how date limits behave, or what the limit parameter controls (likely max results, but not stated). The description gives no usage context on prerequisites or result filtering. An agent cannot reliably construct a correct request without additional knowledge, making the definition incomplete for practical use.

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 0%, meaning no parameter descriptions exist in the schema. The tool description provides no explanations for any of the 6 parameters: case, court, limit, date_to, date_from, language. While parameter names hint at their purposes, an agent does not know what format 'case' should take (e.g., ECLI, case number), what 'court' restricts, or how date filters apply. With zero coverage, the description was expected to compensate, but it stays entirely at the purpose level, leaving all parameter semantics undefined.

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 verb (find), the resource (citing judgments), and specifies the mechanism ('authoritative CELLAR work_cites_work relationships'). It immediately distinguishes itself from keyword-based searches by adding 'never keyword co-occurrence', which sets it apart from sibling tools like search_eu_cases. The purpose is unambiguous and easily understood by an agent.

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 when to use this tool: when you need formal citation relationships rather than keyword matches. The phrase 'never keyword co-occurrence' signals that this is not for keyword search, hinting at an alternative. However, it does not explicitly name the alternative tool (e.g., search_eu_cases) or provide explicit conditions like 'use this when you have a specific case identifier to find citing judgments'. The guidance is clear but not fully explicit.

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