Manage Yunxin app callbacks

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

Annotations already declare readOnlyHint=false and destructiveHint=true; the description earns credit by adding the consequence (修改回调会直接影响消息投递) and the mandatory confirm: true precondition, which annotations cannot express. It does not state whether changes are reversible or what the set call returns.

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?

Two sentences, zero filler, with the operation scope first and the high-risk mutation warning plus confirm precondition front-loaded where an agent will see it before choosing action=set.

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, dual-mode tool with a nested-object parameter and no output schema, the description covers the mutation risk and the required safety flag. It stops short of describing what the get path returns or how callbackFlag keys affect delivery.

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 only 29%, so the description must carry the load, and it does: it maps callbackUrl, callbackTimeout, callbackResult, and callbackFlag to concrete meanings and states the confirm requirement. Only `app` remains undefined in both schema and description.

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 pair (查询/设置) and a specific resource (第三方回调), enumerating the four configurable aspects: URL, timeout, failure policy, and event switches. This clearly separates it from siblings like yunxin_app_get or yunxin_im_config_update, though it never names an alternative explicitly.

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?

The action enum (get/set) plus the statement that modification requires confirm: true gives a clear condition for the mutating path, and the delivery-impact warning warns when caution is needed. It lacks explicit routing rules to sibling tools such as yunxin_im_config_update.

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