Qimen Dunjia & BaZi Charts

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

With no annotations, the description carries the full burden and does well: it declares the engine is deterministic, names what the response contains, and discloses the cost profile ('FREE — no quota consumed'). It does not cover failure behavior (invalid dates, unknown birth time) or whether 'true-solar-time ready' requires a location parameter that the schema does not offer, leaving a small gap.

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?

Roughly four dense clauses ordered purpose → engine → returns → cost → language, with the core purpose front-loaded. No filler sentences and no repetition of the tool name.

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?

There is no output schema, so the description's enumerated return contents (pillars, hidden stems, Ten Gods, strength evidence, geju grade, favorable elements, luck cycle) are necessary and present. What is missing is edge-case handling and clarification of the location-free 'true-solar-time ready' claim, but for a deterministic chart tool the description is largely sufficient.

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%, so the schema already documents all four parameters including defaults and the late-Zi handling. The description only echoes '中文/English via lang' and the vague 'true-solar-time ready', adding essentially nothing the schema does not already state – baseline 3 applies.

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?

Specific verb and resource ('Cast a BaZi (Four Pillars) natal chart') plus concrete mechanism details (solar-term month pillar, Five-Rats hour rule, day master strength chain, geju pattern). It never mentions the sibling qimen_pan, so the distinction relies on the reader knowing these are different divination systems, which keeps it from a 5.

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?

Usage is implied by the artifact produced – you call it when you need a natal chart – and 'FREE — no quota consumed' gives a mild incentive to prefer it. There is no explicit when-to-use versus qimen_pan, no when-not, and no statement of prerequisites such as needing an accurate birth time.

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

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

With no annotations, the description carries the full burden and does well: it discloses the computation method (Zhi Run, verified against a classical ledger), that results are deterministic, the full return payload shape, and that the call is free with no quota consumed. It omits only minor operational details, e.g. whether there are any input-validation constraints or latency considerations.

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 dense sentences with the core action front-loaded and the return payload and cost signal following. No wasted prose, though the parenthetical method citation sits slightly ahead of the more actionable output summary.

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 deterministic computation tool with no output schema and full schema coverage, the description covers purpose, outputs, cost, and language. The only real gap is guidance on choosing between this and bazi_chart for a given divination request.

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%, so all four parameters are already documented at source. The description restates language support ('中文/English via lang') but adds nothing about date format, scene semantics, or defaults beyond what the schema states — baseline 3.

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 verb+resource (cast a Qimen Dunjia chart for a date/time) and enumerates what the chart contains — 9 palaces, deities/stars/gates, void palaces, formations, and a rule-based reading. It does not differentiate itself from the sibling bazi_chart, so an agent cannot tell from the description alone which charting system to pick.

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?

'For a given date/time' implies the trigger (any dated divination request), but there is no explicit when-to-use / when-not guidance and no mention of when to prefer this over bazi_chart. The 'scene' parameter's role in shaping the reading is left implicit.

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