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

GivenreadOnlyHint=true and destructiveHin=false already cover the safety profile, the description adds real behavioral depth: it discloses that both resolved charts are returned, that every cross-chart combination/clash/harm/punishment is named with the two positions it joins, and — distinctly — that the full interaction list ships so a caller can recompute their own score. This 'defensible reading' trait is genuinely useful behavioral information beyond what annotations provide. It stops short of describing score bounds or interpretation thresholds, so not a 5.

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?

Three sentences, roughly a hundred words, with the core action front-loaded in the first sentence and each subsequent sentence earning its place: output composition, recomputation transparency, and intended use cases. No repetition of schema content, no filler. For a tool with this much nested complexity it is remarkably tight.

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 no output schema present, the description compensates well by detailing the return contents in enough depth that an agent knows what to expect. Parameter edge cases are exhaustively handled in the input schema, and the use-case sentence anchors selection among fifteen siblings. The residual gap is that it never explicitly routes the agent away from zodiac_compatibility or toward bazi_chart for single-chart needs, and it doesn't characterize the score scale or how conclusions are phrased.

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 100%: every top-level parameter (lang, compact, personA, personB) and every nested property (date, time, timezone, hourClock, dayBoundary, yearBoundary, longitude, latitude) carries a rich description, including edge cases like DST-correct timezone resolution and the 400 errors for invalid timezone or missing longitude. The description itself contributes no parameter-level meaning, which is fine — the schema already does the heavy lifting. Baseline 3 per the high-coverage rule.

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 opens with a specific verb and resource — 'Compare two BaZi charts pillar by pillar' — and enumerates exactly what the comparison yields (resolved charts, Day Master five-phase relationship, every cross-chart interaction). It distinguishes itself from sibling bazi_chart (single chart) and zodiac_compatibility (sign-level) by framing this as a two-chart, defensible matchmaking reading. The title reinforces the purpose with 'Four Pillars matchmaking API.'

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?

The closing sentence — 'Built for matchmaking products, relationship features, and agents that need a defensible two-chart reading' — gives a clear context for when this tool is appropriate. It does not name siblingalternatives or exclusion conditions explicitly (e.g., 'for asingle chart use bazi_chart'), so an agent must infer the boundary rather than bead told it. Clear context, no exclusions, which matches a 4.

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