Diff Capture

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

The leading '只读' explicitly discloses that the operation is read-only, which is critical because no annotations are provided. The parenthetical also lists the categories of differences reported, helping the agent anticipate the result. It stops short of mentioning preconditions, but the core behavioral trait is clearly stated.

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 a single front-loaded sentence with the safety qualifier first, and the parenthetical adds detail without redundancy. Every element 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 low parameter count and the presence of an output schema, the core purpose, read-only behavior, and expected diff categories are sufficiently stated. The main gaps are explicit parameter documentation and sibling routing, but these are not severe for this simple tool.

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 0% and the description never explicitly names session_id or project_dir. However, '新抓包' and '项目 registry' map naturally onto those two parameters, giving partial inferential help. Explicit mapping and constraints are still missing.

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 ('对比' / compare) and names the resource ('新抓包与项目 registry'), and it enumerates the kinds of differences found (新增/参数变化/未见/鉴权漂移). This is clear enough to distinguish it from generic capture-analysis tools, though it does not explicitly name sibling alternatives.

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 phrase '对比一次新抓包' implies this is used after a capture has been collected and when the agent needs to compare it against the project registry. However, it does not explicitly say when to prefer this over siblings like analyze_traffic or merge_capture, nor does it state any exclusions.

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