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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, and the line '아무것도 바꾸지 않는 계산이다' largely repeats that. It does add useful context that the result mirrors the official tally logic, but says nothing about failure behavior, missing/partial inputs, or what the verdict looks like.

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?

Three short sentences, front-loaded with the action and followed by the key domain caveat. Minimal waste; the 'changes nothing' clause is somewhat redundant given annotations but is brief.

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 8-parameter tool with no output schema, the description never indicates what comes back (a boolean verdict, per-requirement breakdown, margin figures). The input side is adequately covered via schema plus the 집합건물 rule, but the return side is a real gap.

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, and the description adds a genuine cross-parameter rule not in the schema: for 집합건물, both 구분소유자 수 and 의결권(면적) must be supplied for both requirements to be judged. It still omits guidance on the required `preset` key and the redev_* directAttendanceCount case.

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: it takes vote counts and voting rights and judges pass/fail (가결·부결). The 'same function the ballot box uses at counting' line makes the computation's role concrete, though it does not explicitly distinguish itself from siblings like get_resolution_requirement or list_resolution_types.

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?

Usage is implied (call it when you need the verdict), and it gives one real precondition: for 집합건물 you must supply both owner count and voting-right area. But it never says when to use this versus get_resolution_requirement, nor how to choose the required `preset`.

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