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

Annotations already indicate readOnly, idempotent, and non-destructive behavior. The description adds valuable behavioral context beyond annotations: it states the return order ('Returns newest first'), the type of treatment information, and warns that a leading case 'can have hundreds of citing cases,' implying pagination relevance. No contradiction with 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 four tightly packed sentences. It front-loads the core purpose, then adds ordering, use case, and scale context. Every sentence earns its place with no filler or repetition.

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 citation-graph tool with annotations and an output schema, the description covers direction, ordering, typical use cases, and scale. It does not need to explain return values because the output schema exists. The information is sufficient for an agent to select and invoke the tool correctly.

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 description does not directly explain parameters, but 'THIS judgment' maps to the required case_id parameter. Optional parameters (limit, offset, response_format) have schema defaults but no descriptive text. Since schema description coverage is 0%, the description only partially compensates by clarifying the core input.

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 specific verb and resource: 'Walk the citation graph BACKWARD: list later cases that cite THIS judgment.' It clearly distinguishes this tool from siblings (e.g., caselaw_get_citations) by emphasizing the backward direction and adding treatment details like 'followed, distinguished, relied upon.'

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 provides clear context for when to use the tool: 'Most useful on OLDER or landmark judgments' and explains the benefit ('shows whether the case is still followed'). It does not explicitly name alternatives or exclusions, but the backward/forward distinction from sibling tools is evident from the text.

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