Tool Sanitize

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

With no annotations present, the description carries the full burden of disclosing behavior. It clearly lists what the tool strips (JS/OpenAction/metadata/attachments) and explicitly states that body text is untouched, which is critical destructive semantic information. It does not mention side effects around overwriting or output handling, but the core behavioral profile is adequately transparent.

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 compact sentence with a clear colon-led list and a dash-introduced rationale. Every clause adds information: purpose, stripped items, optional toggle, non-goal, and security motivation. There is no filler or redundancy.

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 destructive 7-parameter tool with no annotations, the description provides purpose, scope, excluded behavior, and security rationale. An output schema exists, so return-value documentation is not required here. It would be more complete if it related the output/overwrite parameters to the described sanitation workflow, but the agent can still select and invoke the tool correctly.

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. It usefully maps the strip_metadata, strip_javascript, strip_attachments, and strip_annotations parameters to concrete behaviors, and '正文文本不动' clarifies that no text-modification parameter is intended. However, it does not clarify the required 'path' parameter nor the semantics of 'output' and 'overwrite', which are meaningful for safe invocation.

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 ('剥离' / strip) and a clear target ('发布版脱敏' / release-sanitization), then enumerates exactly which components are removed: JS, OpenAction, metadata, attachments, and optionally annotations. It also states a key non-goal (body text unchanged), which distinguishes it from sibling tools like tool_redact and tool_edit_metadata.

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 '发布版脱敏' gives a clear release/distribution context for when this tool should be used, and '正文文本不动' signals that it is not for content redaction. It does not explicitly name sibling alternatives or state when-not-to-use conditions, so it falls slightly short of a 5.

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