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

With no annotations, the description carries the full burden, and it discloses real behavioral traits: the ranking is a multiple of the usual variation rather than a percentage, causes are deliberately not inferred, holiday weeks distort the verdict and the result carries a '주의' note, and each direction is capped at 30. It doesn't describe the response shape or region identifiers, which keeps it short of a 5.

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?

It is front-loaded: the core behavior comes first, then when to use it, then compact bullets for parameters and caveats. Every line carries distinct information, with no restatement of the name or filler.

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 two-parameter analytical query with no annotations and no output schema, the description covers purpose, usage, parameter semantics, and key caveats. Since there is no output schema, it should say more about what comes back (fields per region, how the '주의' flag appears), which is its main remaining 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 0%, so the description must explain both parameters, and it largely does: `week` defaults to the most recent week and uses the format 'YYYY.MM.N주차'; `top` is the count for each of the increased and decreased lists, capped at 30. The interaction between `top` and the truncation at 30, and what happens to ranking when few regions qualify, is left implicit.

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 gives a specific verb and resource ('returns the cities/counties/districts whose out-of-region inflow deviated most from usual'), and it defines the ranking metric ('multiple of usual fluctuation'). It also differentiates the tool from the manual alternative by telling the agent not to query many regions itself to build a ranking.

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 names the exact question shapes this tool answers ('where was unusual this week', 'where did people suddenly flock nationwide') and states an explicit anti-pattern ('don't query multiple regions yourself and rank them'). The only thing missing is a named sibling for the per-region case, but the usage condition is unambiguous.

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