upc_power_buildings

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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=true, and the description still adds real substance: anonymous access, one fixed public form GET, no credentials or cookies required, and a note that the ids are the school form's live option values rather than a maintained static mapping. That last point is important behavioral context about data freshness that no structured field conveys.

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?

The purpose and scope are front-loaded in the first two lines, and the downstream-id guidance follows logically. The run of negations is dense but each one blocks a plausible misuse, so little could be cut without losing routing value.

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 no output schema, the description carries the burden of explaining returns, and it does identify the key returned field ("id" values as live option value strings) and its consumer. It stops short of describing the accompanying fields in the directory (e.g. human-readable building names or ordering), which an agent formatting results would want.

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?

The tool takes zero parameters, so the documented baseline is 4; the description goes slightly further by explicitly enumerating the argument categories that are rejected (campus, account, URL, header, cookie), which pre-empts an agent trying to pass a campus selector. Nothing further is needed for a no-argument tool.

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 first sentence gives a specific verb and resource ("Read the current official Tangdaowan building-option directory"), and the body explicitly distinguishes it from sibling upc_power_remaining by naming the downstream relationship and by ruling out room queries. An agent can tell what it returns (option ids) 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?

It states the reason to call it ("Use an ``id`` for ``upc_power_remaining``"), the scope restriction ("Only Tangdaowan is supported"), and what is out of scope ("does not query any room, accept a campus, account, URL, header or cookie, or return a room list"). Both the when and the when-not are covered with no inference required.

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