add_summary

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

No annotations are present, so the description carries the disclosure burden. It does reveal that the tool adds/records summary content, and it emphasizes additive recording of user-provided information. It does not explain persistence, whether an existing record is appended vs. replaced, authorization needs, or error/response behavior, which are material for a write tool.

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 well-structured with a front-loaded purpose, trigger, scenario bullets, and explicit parameter guidance. It is a little long, but each bullet earns its place by giving operational guidance rather than repeating boilerplate.

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 simple 2-parameter, no-output-schema tool, the description covers the trigger, content requirements, keyword selection, and usage scenarios, which is enough to call the tool correctly in most cases. Minor gaps remain around return behavior, persistence, and sibling-tool distinction.

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?

Although schema coverage is 100%, the description adds real value: it gives a concrete example for content and a 'one-sentence clarity' rule, and it supplies keyword constraints (no more than 5, prefer specific/independent/relevant terms such as project names or people). This goes meaningfully beyond the generic schema text.

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 clear verb and resource: '添加对话总结到记录中' (add conversation summary to a record), and later gives a concrete trigger ('当用户说"总结记录一下"'). It does not explicitly contrast itself with sibling tools such as save_summaries, so it lacks sibling differentiation.

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 provides clear usage context and scenarios: use when the user asks to summarize/record, when capturing requirements, user-approved information, or project progress/decisions. However, it provides no exclusions or explicit guidance on when to prefer save_summaries/show_summaries instead.

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