zhihu_edit_answer

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

Even though annotations already mark the tool as destructive (destructiveHint=true), the description adds substantial behavioral detail: it modifies live public content, requires a two-step confirm (preview with confirm=false, commit with confirm=true), preserves original content in append mode, and warns that replace mode loses images and rich-text formatting. It also mentions automatic local backup before modification, going far beyond the annotation flags.

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 dense paragraph but every sentence serves a purpose: purpose, confirmation flow, mode semantics, data-loss warning, backup, and permission constraint. It is longer than minimal but justified for a destructive editing tool with multiple modes. The structure could be improved with bullet points, but it remains efficient and 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?

For a complex destructive tool with no output schema, the description covers the workflow, mode differences, data-loss risks, backup, and permission requirements. It does not describe the success response after confirm=true or error scenarios (e.g., authentication failure), but the sibling login tools provide context and the parameters are fully documented. Overall, the description is nearly complete for safe invocation.

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 100%, so the input schema already fully documents all four parameters. The description reinforces parameter behavior (e.g., confirm=false previews, text varies by mode), but adds little meaning beyond what the schema already provides, such as the plain-text caveat already present in the text parameter description. Baseline 3 is appropriate when the schema carries the semantic load.

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 opens with a specific verb and resource: '编辑你【已发布】的知乎回答' (edit your published Zhihu answer), clearly distinguishing this from sibling tools like draft_answer (for unpublished drafts) and get_content (for reading). It further clarifies the two modes (append/replace), making the tool's 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 provides clear when-to-use context: editing one's own published answers, with a two-step confirmation workflow. It explicitly states a constraint, '只能编辑本人发布的回答' (can only edit answers published by yourself), but it does not name alternative tools or explicitly state when not to use this tool in favor of others, so it stops short of full alternative differentiation.

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