保存用户要求为预设

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

No annotations are provided, so the description carries the full burden. It discloses important traits: the dialog channel triggers another server-side confirmation, timeout means no save, and the tool returns potential_conflicts while passing through user_notice verbatim. It also clarifies that semantic conflicts should be handled by proposing an update to the old preset rather than creating a new 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?

The description front-loads the core purpose and the required precondition, then adds output semantics in compact clauses. The final English sentence is slightly redundant with the opening Chinese sentence, but it does not bloat the description. Overall it is appropriately sized and structured.

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?

Because there is no output schema, the description explicitly explains the return value potential_conflicts and the user_notice passthrough, which an agent needs to decide how to handle conflicts. It also covers timeout/no-save behavior and the single-instruction exclusion. For a 7-parameter tool with no annotations, this is sufficient to invoke it 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 100%, so the baseline is 3, but the description adds meaning to content and category by requiring that they be the refined expression and suggested category shown to and agreed by the user. It also reinforces how consent and risk/confirmation policies interlock. This is genuine extra semantics beyond the schema's field descriptions.

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 opens with a concrete action—"把用户确认过的可复用要求保存为预设"—and clearly identifies the resource as a user-confirmed durable requirement. It also adds a scope exclusion: single-use instructions are not stored. It does not explicitly name sibling tools, so differentiation relies on the preset concept rather than an explicit pointer.

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 description states a hard precondition: the user must have seen the refined wording and suggested category and explicitly agreed, with a timeout causing no save. The "单次指令不入库" sentence signals a when-not condition. It does not recommend a specific alternative for single-use instructions, so it stops short of full alternative guidance.

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