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

Annotations already declare readOnlyHint and idempotentHint, so safety is covered. The description adds genuinely non-obvious behavior: factor computation happens server-side and is not returned to the caller, and the subject must be normalized/confirmed before the call. It does not discuss failure modes for invalid inputs beyond the word 'schema 合法的', a minor remaining 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?

Front-loaded arrow-form statement of input to output, followed by provenance guidance and sibling exclusions. Every clause carries routing or constraint information; there is no filler or restatement of the tool name.

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?

With an output schema present, return values need not be explained, and the description covers inputs, provenance, preconditions, and exclusions. It leaves only edge behavior (e.g., what happens when a subject fails validation or when life_topics combine broadly) to inference.

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% and the nested subject fields already carry provenance notes. The description still adds meaning by introducing subject_candidates as an alternate source for subject and by requiring normalization and confirmation, which constrains how the nested standard_time may legitimately be filled.

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 in a single formula: a schema-valid birth subject plus life topics produce a combined BaZi + Ziwei natal reading (八字与紫微本命合参断语). It also names the boundaries against siblings (raw chart tools, annual query), so an agent can tell it apart without opening any schema.

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?

Explicit routing is given: use bazi_chart / ziwei_chart for a bare natal chart, and natal_liunian_query for year-by-year readings. It also prescribes the prerequisite workflow: build subject from explicit user facts or from user-confirmed subject_candidates, and normalize plus confirm when the birth time is fuzzy or multiple candidates exist.

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