读取项目指令

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

Annotations provide readOnlyHint=true, and the description adds behavior beyond that: it describes the layer-by-layer loading from workspace root to target directory and lists both file names searched. There is no contradiction with the read-only annotation.

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 two short sentences with no filler. The main action and method are front-loaded, and the usage timing is appended in a clear second sentence.

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 read-only tool with one optional parameter and no output schema, the description covers what it does, how it traverses directories, which files it loads, and when to call it. Return-value details are not essential given the tool's obvious purpose, though behavior when no AGENTS.md exists is not described.

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?

The input schema has one optional cwd parameter with 0% description coverage. The description compensates by referring to '目标目录' (target directory), which maps to the cwd parameter's intended role. It does not explicitly name the parameter or specify path format, but the meaning is inferable.

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 ('加载'/load) and identifies the exact resource ('AGENTS.override.md 或 AGENTS.md') plus the traversal behavior (from root to target directory layer by layer). It clearly distinguishes this tool from generic file readers like read_file by focusing on project instruction files.

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 explicitly states when to call the tool: '修改代码前应先调用' (should be called before modifying code). It provides a clear trigger condition but does not mention alternatives or when-not-to-use scenarios, so it falls short of a full 5.

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