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

With no annotations, the description carries the full behavioral burden. It discloses the return (severity) and a scope disclaimer (not a diagnosis), but says nothing about input validation, what happens if fewer/more than 7 answers arrive, out-of-range values, or the severity banding thresholds.

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 dense sentence plus a short disclaimer. Every clause adds information (scale, item count, return, scope limit) with no filler, and the core purpose is front-loaded.

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 one-parameter scoring tool with no output schema and no annotations, the description covers purpose, input shape, and the not-a-diagnosis caveat. It still leaves the severity categories and input-validation behavior unspecified, which an agent may need.

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% – the schema only declares 'answers' as an untyped array of numbers. The description compensates by specifying 7 items on a 0–3 scale, which is exactly the semantics an agent needs to construct valid input, though it omits ordering/omission rules.

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 pairing (GAD-7 anxiety symptom scoring), gives the instrument's structure (7 items, 0–3 each), and names the return (severity). The GAD-7 label inherently separates it from siblings like score_phq9 (depression) and score_mood_thermometer.

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?

Offers one usage boundary – '不是診斷' (not a diagnosis) – which tells the agent this is a screening/scoring aid rather than a clinical determination. However, it never says when to prefer this over score_phq9 or the other scoring siblings, leaving selection to inference from the instrument name.

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