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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds real behavioral content beyond that: the response is localised by language, and longitude combined with trueSolarTime affects how the double-hour is cut (a genuine accuracy caveat). It stops short of disclosing cost/tier or error behavior, but the added context is substantive.

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 the aggregate's value proposition, then the enumeration of contents, then the practical solar-time tip — a sensible order. The single dense listing sentence is long and the text is visibly truncated mid-clause ('cut the double-hour fro…'), but there is little filler for a tool of this scope.

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?

An output schema exists, so return values need no explanation, and the description covers the payload contents and the main calculation caveat well. For an 11-parameter aggregate with low schema coverage, the remaining gap is the absence of any statement about when to choose this over its many granular BaZi siblings.

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 36% (roughly 4 of 11 params), so the description carries some of the burden and it partially does: it explains the longitude + trueSolarTime interaction and the language localisation. It says nothing about stageSchool (classical vs unified), includeFullTable, the compact-mode fields/precision pair, or the date/time formats, leaving several parameters undocumented in both places.

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?

Names a specific resource (the full BaZi four-pillar chart) and enumerates exactly what the aggregate returns — hidden stems, na yin, twelve stages, element balance, strength verdict, symbolic stars, interactions. Because the sibling set contains a granular tool for nearly each of those items (astroway_bazi_hidden_stems, astroway_bazi_na_yin, astroway_bazi_element_balance, etc.), the phrase 'everything ... in one call' is precisely the differentiator an agent needs.

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?

'in one call' implies this is the aggregate alternative to the granular BaZi siblings, and the closing sentence gives a conditional ('Pass longitude with trueSolarTime true to...'), which is configuration guidance rather than tool-selection guidance. It never explicitly states when to prefer this over astroway_bazi_four_pillars or the individual endpoints, so the routing decision is left to inference.

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