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

With no annotations, the description carries the full burden and does well: it discloses the non-empty request body requirement, the return contents (total match count plus a case list), the important limitation that `content` is a highlighted snippet or excerpt rather than full text, and that charges/authorization come from the caller's OpenAny gateway. Pagination behavior beyond `top_k` is the main undisclosed trait.

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?

Front-loaded with purpose, then filters, then the response caveat and the routing hint, so an agent gets the essentials first. The final credentials/charges sentence is somewhat boilerplate but justifies itself by explaining the billing and auth model that no structured field covers.

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 an 18-parameter search with no annotations and no output schema, the description covers purpose, mandatory-body constraint, return shape, content truncation, and auth/billing. Gaps are pagination semantics and explicit differentiation from the vector-search siblings.

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 coverage is 100%, so the baseline is 3, but the description adds one thing the schema cannot: that the request body must not be empty even though zero parameters are required. It also groups the filter families in prose, giving a quick mental model of the 18 fields before the agent reads each schema entry.

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 opening sentence gives a specific verb and resource ('Searches for a list of ordinary adjudicated cases') and the filter list makes the scope concrete. It explicitly distinguishes itself from the case detail API at the end, but never contrasts itself with the semantic/vector case search sibling, so an agent must infer the keyword-vs-semantic split from the tool name.

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 names an alternative and the condition that selects it: 'Call the case detail API when full text is required,' which is a genuine routing rule an agent can act on. It does not say when to prefer this over the vector/semantic search tools, so the guidance is clear but incomplete.

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