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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered; the description adds genuine behavioral detail, notably that semantic mode silently falls back to keyword when the embedding model is unavailable and that the response's 'mode' field reports which ran. That fallback disclosure is exactly the kind of surprise an agent needs warned about. It stops short of describing the shape of returned paragraphs or how limit interacts with total result counts.

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 and sibling differentiation are front-loaded in the first two short paragraphs, followed by an Args block that is dense but earns its space given 0% schema coverage. The per-parameter list is longer than ideal but every line adds information not present in the schema.

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 10-parameter read-only search with no output schema and only minimal annotations, the description covers every parameter, defaults, and the mode fallback behavior. It does not describe what a returned paragraph contains (fields, citation anchoring, ordering) or whether limit truncates silently, which leaves a modest gap for a tool whose whole purpose is extracting quotable text.

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%, so the description carries the full load and does so well: it explains term with examples, gives the exact allowed disposition values (allow, dismiss, grant, quash, refuse, remit) and jurisdiction strings that are not enums in the schema, and documents topic as a multi-select list with slug examples. Gaps remain for court (no code format, and list_courts exists as a sibling) and domain (no slug example), so it is not fully self-sufficient.

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 first sentence gives a specific verb (Find) and resource (specific paragraphs across cases) with the subject matter constraint (discuss a legal concept). It explicitly contrasts with the sibling search_cases by naming case-level vs paragraph-level results, so an agent can pick between them without opening either schema.

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?

It states the positive condition plainly — 'Use when you need quotes or specific language from judgments' — and names the alternative (search_cases) together with the reason to prefer this tool over it. Nothing about tool selection is left to inference.

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