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

Annotations already declare readOnlyHint=true, idempotentHint=true and destructiveHint=false, so the safety profile is covered and the bar is lower. The description adds a genuinely non-obvious output-semantics caveat ('On the four storage branches the middle role belongs to the stored element, not to the second in the list'), which is useful interpretive context. It does not cover return shape, auth, or limits, so it earns a middling score rather than a high one.

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 core concept and reasonably short, but the middle sentence ('This is where most of a chart's elements live: a chart with no visible Water can still be soaked in it') is evocative illustration rather than functional guidance. The group/cost tags are compact and useful, but the descriptive rhetoric could be trimmed without loss.

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 an 11-parameter tool with only 36% schema coverage, the description omits everything an agent needs to invoke it correctly: no param semantics, no usage context, no sibling routing. An output schema exists so return values need not be explained, but the input and selection gaps are substantial.

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% (11 params, ~4 described), so the description must compensate and it adds zero parameter information. Required 'date', 'time', 'language', 'stageSchool', 'trueSolarTime', and 'includeFullTable' are unexplained in both schema and description. The 'role and weight' and 'storage branches' language refers to output, not inputs, so it does not close the gap.

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 defines the concept (the one-to-three stems each branch shelters, with role and weight) and clearly belongs to the Hidden Stems domain, distinguishing it from other BaZi siblings by topic. However, it never states the action a verb+resource framing would give ('returns the hidden stems for a chart built from the supplied date'), leaving the agent to infer that this computes data rather than explains it. Concept is specific; the operation is only implied.

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?

No when-to-use guidance, no prerequisite conditions, and no named alternatives among the many BaZi siblings (bazi_four_pillars, bazi_element_balance, etc.). Nothing tells the agent when hidden-stem data is the right call versus, say, the element balance tool that uses the same underlying concept.

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