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

Annotations already declare readOnly, idempotent, non-destructive, closed-world, so safety is covered. The description still adds real behavioral value: results are sorted with the highest case counts first and each entry includes a case count, which shapes how an agent should interpret the returned ordering. Return format itself is covered by the output schema, so no penalty there.

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?

Two short sentences with zero filler. The primary capability and the sort behaviour are front-loaded, and the disambiguation sentence follows immediately.

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?

With a full input schema, a declared output schema, and complete annotations, the description supplies everything needed to select and call the tool. The only omission is that it never signals pagination exists, though cursor and limit are self-documenting in the schema.

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 100%, so name, district, limit, cursor, and purpose are all documented in the schema with more precision than the description gives. The description only echoes "by name and district" and adds no matching semantics (substring, case handling) or pagination guidance beyond what the schema already states. Baseline 3 applies.

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?

States a specific verb and resource (list judges), the filterable attributes (name, district), the sort order (most cases first), and what each row carries (case counts). It also explicitly names the sibling it is not: get_judge. An agent can distinguish it from every search_* sibling without opening a 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?

"get_judge gives one judge in full" explicitly routes the agent to the alternative for the single-record case, which is the main ambiguity here. What's missing is any exclusion for the adjacent case (search_cases when a judge's rulings, not judges, are wanted), so selection is clear but not fully framed.

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