generate_product_detail

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

Annotations already declare readOnlyHint=false, openWorldHint=true and idempotentHint=false, but the description adds real behavioral context beyond them: the title is auto-normalized to Alibaba title case, writes via `save_to` are confined to the server's allowed directories, and token usage is recorded (pointing at `usage_stats`). It stops short of describing failure modes or API/permission requirements for a non-idempotent, LLM-backed generation call.

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?

Three tight sentences: output shape front-loaded, then parameter semantics, then side effects. No filler, no restatement of the name, and the parenthetical details are load-bearing.

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?

An output schema exists, so return values need not be described, and the description covers the generation contract, the file-write side effect with its sandbox constraint, and cost accounting. The main remaining gap is guidance on the many unlabeled input parameters (tone, language, detail_image_count), which an agent must infer.

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% across 11 parameters, so the description carries the entire burden, yet it only explains three of them (brands, version, save_to). It does add non-obvious value the schema lacks — the version enum meanings (premium/lite/general) are absent from the schema, and the brand-casing rule is a real semantic detail — but tone, features, keywords, language, target_market, detail_image_count, and extra_instructions remain unexplained.

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?

Specific verb ('Generate') + resource ('structured product detail') with an explicit enumeration of the produced artifact (title, highlights, image+text modules, attributes, keywords, FAQs). This sharply distinguishes it from siblings like generate_social_content and product_render_draft without needing schema inspection.

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 gives conditional hints for individual parameters (when to pass `brands`, what `save_to` does, what `version` accepts), but never states when to choose this tool over alternatives such as product_publish_from_brief or generate_social_content, nor any exclusions or prerequisites. Usage is implied by the output artifact rather than stated.

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