寫檔案

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

With no annotations, the description carries the full burden of behavioral disclosure. It reveals two key behaviors: automatic parent directory creation and that it does not perform partial merges. This is helpful, though it could mention side effects like permanent deletion of existing content or permission requirements, but the current disclosure is adequate for a simple 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 extremely concise—two short clauses. It front-loads the core purpose and key behavior (auto-create parents) and includes a critical exclusion (no partial merge). Every word earns its place, with no filler or redundant phrasing.

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 two-parameter write tool with no output schema, the description covers the essential operational behaviors: create/overwrite, parent directory creation, and the no-partial-merge restriction. Missing details like error handling or return values are not critical given the tool's simplicity, but a mention of whether the operation is atomic or what happens on missing directories would make it more complete.

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%, so the description must compensate for missing parameter meaning. The description only mentions 'file' and 'content' implicitly through 'create new file' and 'overwrite', but does not elaborate on path format, content encoding, or how the two parameters interact. Since the schema provides only types and no descriptions, the tool relies on the parameter names being self-explanatory, which is insufficient for an agent to understand edge cases or expected formats.

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 clearly states the tool's action (create or overwrite), the resource (file), and explicitly contrasts with partial merging, which distinguishes it from siblings like fs_edit. The 'complete overwrite' and 'does not do partial merging' clauses make the purpose unambiguous.

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 defines when to use the tool (creating new files or fully overwriting) and when not to (when partial merging is needed). However, it does not explicitly name the alternative tool (fs_edit) as the HIGH calibration example did, leaving the alternative selection slightly implicit.

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