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

With no annotations, the description carries the full burden. It usefully states the output is a severity result and adds the non-diagnostic caveat, but omits how the result is formatted, the severity banding, and any validation behavior when answers are malformed.

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?

A single compact sentence with a bracketed guide prefix; the verb, scale, and scoring range are front-loaded and the caveat closes it. Every clause contributes, though the bracket tag is minor overhead.

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?

There is no output schema, and the description only says it returns severity without describing the returned structure or banding. For a simple one-parameter scoring tool it is mostly adequate, but the result format remains unspecified.

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% and the schema only says 'array of numbers'. The description compensates meaningfully by specifying 7 items scored 0–3, which constrains the array's expected length and value range. It does not clarify ordering or what happens on out-of-range values.

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 (計分/scoring) and resource (GAD-7 焦慮症狀) with clear scope (7 題 0–3 分). An agent can distinguish it from wellness__score_phq9 or score_mood_thermometer by the named scale, though it never explicitly references the siblings.

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: apply this when you have GAD-7 item scores. The closing '不是診斷' (not a diagnosis) gives a useful applicability boundary, but there is no explicit guidance on when to choose this over the PHQ-9 or mood thermometer siblings.

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