prepare_chat_summary

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

Annotations already establish readOnly, non-destructive, closed-world behavior. The description adds real value beyond that: it discloses that the tool returns an evidence package with per-person/day statistics and per-group rule candidates, and that natural-language summarization is done by the caller, which shapes how the agent should expect to use the output.

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?

Two dense sentences with no filler; the core purpose and the division of labor with the calling AI are front-loaded. The focus enumeration is long but serves the enumeration of supported use cases.

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 12-parameter tool with a nested offsets object, two enums and no output schema, the description leaves most parameter semantics and the shape of the evidence package unexplained. It conveys the concept of the output but is not sufficient for an agent to invoke the tool correctly across its many options.

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?

With 12 parameters and 0% schema description coverage, the description carries the full documentation burden but only references the focus categories, implicitly mapping to one enum parameter. The other eleven parameters (offsets, time windows, keywords, match_mode, sender_ids, context windows, per_session_limit) receive no explanation in either schema or description.

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 states a specific verb+resource ('prepare a citable evidence package') and enumerates the focus categories it supports. It also distinguishes its role by noting the calling AI completes the summarization, which separates it from a summary-generating sibling like analyze_wechat_chat, though no sibling is named explicitly.

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 focus list implies the scenarios (daily/weekly reports, project progress, risks, etc.), giving a soft sense of when the tool fits. However, there is no explicit when-to-use versus alternatives guidance and no exclusions, leaving the agent to infer the comparison with siblings such as analyze_wechat_chat.

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