edit_variant

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

Without annotations, description carries full burden. It reveals key behaviors: zero LLM involvement, only patches passed fields, marks manual edit state, returns a snapshot. Missing details on overwrite vs merge and permissions, but sufficient for safe invocation in most contexts.

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?

Description is brief with one-line purpose, bulleted parameters, return spec, and follow-up advice. No wasted words, information is front-loaded and scannable.

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?

Given 3 parameters and no output schema provided in input, description covers all necessary aspects: behavior, parameter details, return structure, and post-edit action. Adequate for an agent to use 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 coverage is 0%, so description must compensate. It explains thread_id, item_id as string, and patch with fields stem?, answer?, analyze? (mapping analyze to solution field). Clarifies that None keys are unchanged. Adds meaning beyond bare schema.

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?

Description states '手动编辑某道变式（零 LLM，只 patch 传入字段）→ 标手动编辑态。' which clearly identifies the verb (manually edit), resource (variant), and specific scope (no LLM, only patch fields, marks manual state). This distinguishes it from siblings like generate_variants or verify_variant.

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?

Description includes '改后建议重跑 verify_variant' providing a post-edit recommendation. While it doesn't explicitly contrast with alternative tools, the context implies use for manual tweaks after generation. No exclusion criteria, but the guidance is clear enough.

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