开始记忆整理

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

With no annotations provided, the description carries the full behavioral burden. It discloses that the call returns the full library and health metrics, that the agent should produce a proposal list, and that changes are applied later via apply_consolidation rather than automatically. It does not explicitly state whether any internal state is modified, but the 'user-driven, then apply' framing strongly implies this call itself does not apply changes.

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 is dense and front-loaded, starting with the key call condition. The Chinese portion carries detailed actionable guidance, while the trailing English sentence 'Start a user-initiated consolidation pass' is somewhat redundant with the title and opening clause, but the overall text remains focused and every other sentence earns its place.

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?

Given the absence of an output schema, the description adequately explains return values (full library and health metrics) and the expected deliverable (a proposal list covering deduplication, contradiction resolution, refinement, retirement, and skill clustering). It also specifies the user-driven decision flow. A more complete description could outline the exact proposal-list format, but the current text gives enough context for correct invocation and downstream behavior.

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 tool has zero parameters)Skip? Actually the schema has no properties, so there is no parameter semantics burden. The baseline for a 0-parameter tool is 4, and the description appropriately uses the space to explain the intended workflow rather than inventing parameter details.

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 names a specific verb+resource: starting a memory consolidation pass only on user request. It also differentiates itself from the sibling apply_consolidation by explicitly saying that the proposal list is landed via apply_consolidation, so the agent can tell the two tools apart.

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 opens with an explicit usage condition: '仅在用户主动要求整理记忆时调用' (only call when the user actively requests memory consolidation). It further clarifies that the process is user-driven and that apply_consolidation is the tool that applies the changes, making the division of labor between sibling tools explicit.

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