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

Annotations already declare readOnlyHint=true, idempotentHint=true, openWorldHint=false and destructiveHint=false, so the safety profile is covered without description help. The description does add one thing the annotations do not: a 20-credit (Tier 2) cost, which is decision-relevant for a metered API. It says nothing about failure modes, data requirements, or the difference between 'computed' here and any cached variant.

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?

A single dense sentence plus two bracketed metadata tags, with no filler or repetition and the chart contents front-loaded. It is a long list-like sentence, but every listed element is substantive rather than padding.

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 14-parameter, 5-enum, cost-metered computation tool with heavy sibling overlap, the description leaves out the essential call prerequisites (birth date/time/gender) and the school/divide options that materially change output. The output schema does relieve it of explaining return values, but the input side is too thin for an agent to invoke this confidently without opening the schema.

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 description coverage is only 29%, so the description is expected to compensate and it does not: it never mentions that date, time and gender are required, nor explains the four 'school' variants, yearDivide/dayDivide/tianmaSchool options, or fixLeap. Only two parameters (fields, precision) and part of timezone carry schema descriptions; the description adds no parameter meaning at all.

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 lists the specific Zi Wei Dou Shu contents produced (soul/body palaces, five-element class, 14 main stars plus auxiliaries, twelve stages, 12 decade limits, 四化), so the resource is identifiable. However it is a content enumeration rather than a stated action, and it gives no differentiation from the closely named sibling astroway_ziwei_full_chart or from astroway_ziwei_main_stars / astroway_ziwei_four_transformations, which appear to cover subsets of the same material.

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?

There is no when-to-use guidance, no prerequisites, and no mention of alternatives. The only routing information is a group tag ('Zi Wei Dou Shu') and a credit cost, neither of which tells an agent when to pick this tool over the ziwei_full_chart or per-palace siblings.

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