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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, so the safety burden is lifted. The description adds substantive non-obvious behavior: tradition-dependent outputs for three stems with all school readings shipped in schoolVariants, plus the 10-credit cost. Auth and rate-limit details are absent, but nothing material is hidden.

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 with what is computed, then the tradition nuance and the school switch; every sentence carries information. The trailing [Group]/[Cost] tags are structured metadata rather than prose, so they don't dilute, though the second sentence's 'computable without star placement' clause is loosely placed.

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 annotations cover safety. For a 7-param tool the description covers purpose, tradition variance, and the key enum, leaving only minor gaps around the required birth date and the compass of the other params, which the schema largely handles.

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 moderate (57%): fields, timezone, precision, and timezoneOffset are already documented, while date, time, and school are not. The description compensates meaningfully for the undocumented `school` enum by explaining that it selects the headline answer and that variant readings appear in schoolVariants, adding real semantics beyond the bare enum.

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 computation (the four stars 化禄/化权/化科/化忌 activated by the birth-year stem) with domain-accurate detail, and adds the crucial scoping fact that this is the one part of Zi Wei computable without star placement. An agent can distinguish it from ziwei_chart, ziwei_main_stars, and the palace tools 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?

Gives clear contextual guidance on when the school parameter matters: seven stems agree across traditions, three (戊庚壬) do not, and `school` switches the headline answer. It does not, however, explicitly route the agent relative to sibling tools or state prerequisites for the required date input.

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