Summarize a past conversation

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 states the summary is 'extracted deterministically without an LLM,' which is a useful behavioral trait. However, it does not explicitly state whether the tool is read-only or has side effects, leaving some ambiguity. For a tool that likely only reads data, mentioning it does not modify the conversation would improve transparency.

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 consists of two concise sentences. The first sentence defines the output format (handoff card with five fields). The second sentence provides usage guidance and comparison to sibling. No extraneous information; every 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 tool has 2 parameters, no output schema, and no annotations, the description adequately explains the return format (a structured handoff card) and the deterministic extraction method. It also guides usage in context of long sessions. However, it could be more complete by mentioning what the tool does NOT include (e.g., full conversation text) to set expectations further.

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 baseline is 3. The description does not add any additional meaning about the parameters beyond what the schema already provides. The schema's descriptions ('conversation id from list_conversations' and the list of allowed sources) are sufficient, and the description doesn't need to repeat them.

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 uses a specific verb 'Return' and describes the output as a compact 'handoff card' with five deterministic fields (目标/已完成/卡点/待办/最后状态). It explicitly distinguishes from sibling tool 'get_conversation' by noting it is for long sessions, making purpose clear.

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 'Prefer this over get_conversation for long sessions' and explains why (carries intent/next-step at fewer tokens). This provides clear guidance on when to use the tool vs the sibling, though it does not explicitly mention when not to use it.

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