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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), and the description adds substantial context beyond them: 5 credits per call charged only on success, a free sandbox key, full determinism with no model called, the enumerated verdict vocabulary, that cautions are surfaced with the source book named, and that ambiguous stone names return candidate lists. This is exactly the extra disclosure the dimension rewards.

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?

Well front-loaded: trigger, then semantics of the answer, then returns, then cost. It loses a point for internal repetition — determinism is asserted twice ('Deterministic: no language model is called' and 'Deterministic: the same input always gives the same answer') and the prescription/not-future point is restated as 'Nothing here predicts what a stone does'.

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 nested, multi-parameter tool with an output schema, the description covers everything an agent needs: the trigger, the resolution of ambiguous inputs, the conflicting-stone check, the charged/un-charged cost model, and the determinism guarantee. Return-value detail is supplemented rather than duplicated, which is appropriate given the output schema exists.

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; the description adds real meaning on top by explaining how the `gem` value is resolved (English or Indian name, multi-stone words answered with candidates) and that `alsoWearing` is checked against the source-listed incompatible pairings when the planet is in scope. It also reinforces that birth time is required rather than optional.

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 opening sentence states a specific trigger verb and resource — deciding whether a gemstone should be worn, or whether a worn stone suits the chart — and explicitly bounds the scope as 'the prescription, not the future'. No sibling tool (get_chart, get_forecast, get_guidance) does gemstone prescription, so the agent can route here without ambiguity.

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?

Clear when-to-use conditions (user asks about wearing a stone, or whether a worn stone suits the chart) plus a scoping exclusion ('Nothing here predicts what a stone does'). It stops short of naming the alternative sibling an agent should use for predictive questions, so the exclusion is left implicit rather than routed.

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