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

Annotations already cover idempotency and non-destructiveness, but the description adds genuinely new behavior: login required, no notification is sent, no friend relationship created, and a 404 should not be retried. The idempotent claim merely restates the annotation, but the 404/no-notification details are substantive additions.

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?

Dense and front-loaded: the login requirement is bracketed first, then constraints, then routing and chain. Very information-efficient for the space, though the bracketed multi-clause style is slightly cramped.

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 single-parameter idempotent follow tool with no output schema, the description supplies login requirement, side-effect profile, error handling, list location, and the correct orchestration chain. Nothing an agent needs to invoke it correctly is missing.

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 100% and productId is fully documented as a cuid sourced from get_product/search_products. The description adds only a weak constraint (产品 must be 已发布/published) and no new parameter semantics beyond the 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?

States a specific verb+resource: 关注 (follow) a 已发布产品 (published product). It explicitly distinguishes itself from the sibling follow_creator by naming it and clarifying that 交友 (making friends) belongs there, not here.

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?

Explicit routing: follow list lives in get_my_card, friend-making goes to follow_creator, and the combination chain (get_product→关注; get_creator→start_conversation) tells the agent the correct precondition sequence. This is when/when-not guidance plus alternatives.

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