Manage IM digital humans

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

Annotations already declare readOnlyHint=false and destructiveHint=true, so the safety profile is known. The description adds value by flagging that delete/rag_embed need confirm: true, which the annotations do not convey. It stops short of saying what is actually destroyed (a digital human persona? its knowledge base?), whether deletes are recoverable, or what rag_embed training costs in time.

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 dense line with zero filler; the action enumeration is front-loaded and the confirm rule closes it. The terse comma-separated listing is efficient, though the lack of any separation between the CRUD group and the rag_* group slightly blunts scanability.

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 destructive, multi-action tool with nested free-form objects and no output schema, the description should explain what belongs in data/params for each action. It does not, leaving the agent to guess payload shape for add/update/rag_embed — the highest-risk operations here.

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 0%, so the description carries the full burden and largely fails it: of seven parameters, only action and confirm are addressed. The meaning of app, data, params, limit, and createTime is left entirely undocumented, and for a tool where data/params are free-form nested objects whose expected keys differ per action, that is a serious 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 enumerates all eight action verbs against the resource (list/get/add/update/delete plus the three rag_* document operations), so an agent knows precisely what capability set is behind this multiplexed tool. It does not, however, distinguish itself from near-neighbours such as yunxin_im_robot or yunxin_im_lexicon, which also manage IM sub-entities.

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?

There is one real usage rule: delete and rag_embed (train) operations require confirm: true. That is genuinely helpful routing guidance. But nothing says when to pick this tool over yunxin_im_robot, nor when rag_list versus get is appropriate, and there are no stated prerequisites or side-effect conditions.

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