召回适用预设

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

With no annotations provided, the description carries the full burden and does so well: it discloses that the server may pop a confirmation dialog, enumerates the terminal states, and mandates verbatim relay of user_notice. This gives an agent clear behavioral expectations beyond the schema.

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 front-loaded with the core call timing and purpose, then lists terminal states and follow-up actions efficiently. The English summary at the end repeats the Chinese content, adding slight redundancy, but there is no filler.

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?

Despite having no output schema, the description enumerates the return terminal states and their required actions, which is nearly complete. It does not specify the exact JSON response shape beyond those states, but for a tool with three optional parameters this is a strong definition.

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 100%, so the parameter descriptions already explain mode, project, and task_type. The tool description itself adds no parameter-specific detail beyond the schema, so the baseline of 3 applies.

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 specific verb and resource: '开始任务时调用，召回适用于当前上下文的预设并完成确认'. It clearly distinguishes what the tool does from the sibling memory-management tools, and the terminal-state list plus the record_usage handoff further clarify its role.

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?

It explicitly states when to call it ('开始任务时调用') and gives handling guidance for each terminal state, including reporting pending_confirmation results via record_usage. It also distinguishes interactive vs unattended mode, but it does not explicitly say when not to use it or contrast it with list_memories/memory_overview.

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