kingdee_validate_bill

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

Consistent with readOnlyHint/idempotentHint/destructiveHint=false via '不真正保存', and adds genuine behavioral color: sub-second feedback ('秒级反馈') and the failure taxonomy (auto_fixes, missing_required, entry_issues). Slightly redundant in that it enumerates return fields that the output schema already declares.

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 purpose and the key 'does not save' qualifier, then a scannable bullet list, then the recommended workflow. The return-field list is somewhat duplicative of the output schema, which costs a bit of tightness.

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?

An agent has everything needed: what it does, that it is safe and non-persisting, what kinds of errors it surfaces, and the exact sequence to follow before saving. Return values are also covered by an output schema, so no meaningful gap remains.

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?

The description adds one useful semantic point — 'is_new: model 无 FID' — which clarifies how the model parameter encodes create vs update, and '缺失的顶层必填字段' hints at the expected structure. But it says nothing about form_id, is_delete_entry, or need_update_fields, which are present in the schema and whose relevance to a non-saving validation is unclear; a low reported schema-coverage figure means the description should compensate more.

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: pre-save validation of a bill model, explicitly '不真正保存' (does not actually save). This clearly separates it from the write path kingdee_save_bill and from other mutation siblings such as audit/submit.

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?

Gives an explicit workflow: validate first, fix per suggestions, then call kingdee_save_bill so it succeeds the first time. The alternative (kingdee_save_bill) and the condition selecting this tool are both named, no inference required.

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