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

With no annotations supplied, the description carries the full burden, and it does disclose the single most important behavioral trait: the returned order is an unpublished, incomplete ranking, which stops an agent from treating it as an authoritative league table. It also discloses that results are 'top' schools rather than an exhaustive list and that output feeds get_school_hotspots. It stops short of describing pagination, record fields, or failure behavior.

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 a single dense sentence that front-loads the scope (year, city, type) before the ranking caveat and the chaining hint, with no filler. The parenthetical about the unpublished ranking metric is long but earns its place as the key caveat.

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 four-parameter, read-style lookup with no output schema and no annotations, the description covers the query scope, the reliability caveat on ordering, and the natural next step. It could say more about what a returned school record contains or whether there is a result cap, but nothing essential for a correct call is missing.

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 the schema already explains year (民國年), city, the schoolType enum, and the 'ALL' or '縣市|鄉鎮' format for area. The description adds only marginal meaning by noting the township constraint is optional ('可再限定鄉鎮'), leaving everything else to the schema — the baseline 3 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?

The description gives a precise verb+resource (查詢…排名前列學校) scoped by year, city, optional township, and school type, and it explicitly warns that the ordering only looks like a ranking and is neither a published metric nor a complete ranking. It also names the sibling it chains into (get_school_hotspots), so an agent can tell the tool apart without opening any 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?

Usage is only implied: it says results 'can be chained to get_school_hotspots', which hints at a downstream workflow but never states when to pick this over siblings such as list_schools or get_school_hotspots, and gives no exclusions or prerequisites. The audience must infer that this is the entry point for ranked-school queries.

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