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

With readOnlyHint=true and destructiveHint=false in the annotations, the safety profile is already covered, so the bar for additional credit is lower. The description adds genuine behavioral context beyond that: the two schools genuinely disagree on the year boundary, the choice is a request parameter, and the resolved convention is echoed back so the answer is self-describing. It also discloses the enriched result shape (animal, pillar, element), which matters because no output schema exists.

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, each earning its place: the first states the core resolution and enriched output with a concrete example, the second flags the genuine ambiguity and how it is handled, and the third names use cases. The core action is front-loaded before any nuance, with zero filler.

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, the description correctly shoulders the burden of conveying return values — it names the zodiac animal, sexagenary pillar, Five Element phase, and the echoed convention. It also covers the one genuinely surprising behavior (January/February boundary disagreement), and the readOnly annotation covers safety. It does not explicitly distinguish itself from the get_chinese_astrology_zodiac_animals list tools, which a cautious agent might conflate with it.

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 individual parameter descriptions are already rich, so the baseline is 3. The tool description adds value above that by explaining why yearBoundary exists (school disagreement) and framing the date as 'a property of the year', plus the schema documents compact's lossless columnar tradeoff. The Metal Horse example also clarifies the output semantics that the parameters feed into, tying parameters to behavior.

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 uses a specific verb and resource: 'Resolve a birth date to its Chinese zodiac animal, the sexagenary year pillar behind it, and the Five Element phase of that year.' The concrete example (1990 → Metal Horse rather than Horse) makes the enriched scope unmistakable, and the focus on birth-date resolution with enriched output separates it from the sibling animal-list and BaZi routes.

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 description explicitly names intended use cases: 'Built for sign lookups, onboarding forms and birthday features.' The yearBoundary parameter documentation goes further, telling agents this route answers the folk question and that 'the BaZi routes default to li-chun instead, because a chart and a folk sign are answering different questions' — an explicit when-not that routes agents away from the BaZi siblings. It stops short of naming the alternative list-lookup tools directly.

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