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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and a closed world, so the safety profile is covered. The description adds behavior beyond that: the two-phase call pattern and the fact that the empty call is a question-fetch rather than an error, plus the non-diagnostic caveat. It stops short of describing the bands or the maximum score, which is a minor gap.

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?

Three sentences, front-loaded with the identity of the instrument, then the call sequence, then the input encoding, then the caveat. No sentence is redundant and nothing is buried.

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 compensates by stating what comes back in each mode (questions and scale, then score and band). For a single-optional-parameter, read-only tool, an agent has everything needed to invoke it correctly in both phases.

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 100%, so the baseline is 3, but the description exceeds it by supplying the meaning of each value on the 0–3 scale (never, sometimes, most of the time, almost always), which the schema does not label. It also makes clear that the parameter is optional by describing the no-argument call.

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 names the specific instrument (PGSI, a validated 9-question screener) and states exactly what the tool produces in each mode: the questions when called empty, a score and band when called with nine answers. An agent can distinguish this from siblings like block_gambling or find_gambling_help purely from the text.

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 gives an explicit operational protocol — call without answers, ask the user each question, then call again with the nine responses — which is stronger guidance than most tools provide. It also sets the boundary 'screening tool, not a diagnosis', though it never explicitly contrasts itself with the sibling help or blocking tools.

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