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

With no annotations, the description carries the full burden, and it does add real value by disclosing the exact output shape (one relation line, one sourced quotation, one three-minute practice) and that the call is free. It omits whether the content is cached/fixed for the day, whether any auth or rate limit applies, and what happens for an invalid stem — meaningful gaps for an unannotated tool.

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 front-loaded sentence with a colon-delimited breakdown of the returned card. Every clause carries information — scope, contents, cost — and nothing is padded.

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 simple two-parameter read tool with no output schema and no annotations, the description successfully substitutes for the missing output documentation by listing the three card sections. It falls slightly short on freshness semantics ('today' in which timezone?) and error behavior, but is otherwise sufficient to call correctly.

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 50%: day_master is documented with its ten-stem domain, and the description reinforces it as the scoping input ('for a Day Master'). The lang parameter is covered only by its enum, with no prose on default behavior or whether omitted lang falls back to a system locale.

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 concrete resource (today's Mingpath card) tied to a specific input concept (a Day Master) and enumerates the card's three components, so an agent knows exactly what comes back. It does not explicitly contrast itself with siblings like bazi_chart or ziwei_chart, which is the only thing keeping 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?

'Today's ... card' implies a once-per-day, low-commitment retrieval for a given Day Master, which is enough to infer a basic use case. However, there is no explicit statement of when to pick this over a full chart tool, nor any prerequisite or exclusion guidance.

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