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

Annotations declare readOnly/idempotent/non-destructive, and the description reinforces and extends these honestly: it asserts 'Deterministic', names the production engine and conventions, explicitly excludes interpretation ('Facts only: no strength verdicts, no favorable elements'), and dictates the never-show-raw-JSON rule. This is rich behavioral disclosure fully consistent with the annotations — no contradiction.

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 description is long but every sentence earns its place: correction order, output contents, presentation routing, exclusions, engine reference, determinism, and the JSON never-display rule are all load-bearing for correct invocation. Purpose is front-loaded ahead of the formatting constraints. Slightly dense, but appropriately so for a tool with complex presentation requirements.

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?

Exceptionally complete given the complexity: an output schema exists, all 9 parameters are documented, and the description covers purpose, correction mechanics, output composition, presentation rules, behavioral exclusions, engine provenance, and determinism. Nothing an agent needs to call it correctly and format the result safely is missing.

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 schema documents every parameter. The description adds genuine interconnect value by explaining that timeZone + longitude feed the true-solar-time correction pipeline, which gives semantic meaning beyond individual field definitions. This is a modest value-add over a complete schema, so the baseline 3 holds.

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?

Opens with a specific verb + resource ('Cast a BaZi / Four Pillars chart the right way round') and immediately names the defining constraint (true solar time correction FIRST). The title reinforces the differentiator. Purpose is unambiguous and self-evidently distinct from the sibling tools compose_sketch and personality_sketch.

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?

Provides solid operational guidance on how to present output (the card-widget vs. raw-scroll branches, never showing raw JSON), which is a form of usage context. However, it never names alternatives or exclusion conditions — there is no 'use X instead when Y' guidance relative to compose_sketch or personality_sketch. The when-to-use context is implied by the tool's specificity rather than stated.

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