Tool Redact Text

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

With no annotations, the description carries the burden and reveals destructive effects: redacted pages are rasterized, text is physically deleted, and other pages retain their text layer. It does not cover output/overwrite side effects, but the core mutating behavior is explicit.

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 terse sentences plus a concrete example convey the action, workflow, and destructive side effects with no filler. The key behavior is front-loaded.

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?

The description is sufficient for the core redaction scenario but incomplete for optional output behavior: it does not clarify how dpi, overwrite, output, or rasterize_all alter the result. Since an output schema exists, returns are covered, but the overall tool behavior is not fully specified.

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 coverage is 0%, so the description must explain parameters, but it only clarifies 'queries' as keywords. 'path', 'dpi', 'output', 'overwrite', and 'rasterize_all' receive no meaningful explanation, leaving most parameters under-specified.

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?

Identifies a precise action: automatically locate every occurrence of given keywords and black them out by content, without manual coordinates. The phrase '按内容' and the example distinguish it from coordinate-based redaction tools and sibling tool_redact.

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 example '把所有合同编号涂掉' and the automatic keyword-location behavior make the intended use case clear. It implies a content-driven redaction workflow, though it never explicitly names alternatives or says when not to use it.

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