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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, so the safety profile is covered. The description adds valuable behavioral context beyond annotations: the 'all' chip is always first, chips below minCount are not sent by the server, missing occupations don't mean no such people, and logged-in vs anonymous counts differ (cloud users included when logged in). This is rich behavioral disclosure that helps the agent interpret results correctly.

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 structured with clear section headers (【何时用】【组合链】【口径】), front-loads the primary use case, and every sentence carries information. It is dense but not bloated, and the formatting makes it easy for an agent to parse. No wasted words.

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 zero-parameter, read-only, idempotent tool with no output schema, the description covers everything an agent needs: when to call it, what it returns, how the data behaves, how it relates to siblings, and the exact chain to use. The only minor gap is that the return format isn't formally specified, but the description's field explanation (key/label/count) compensates. Complete for this tool's complexity.

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?

The tool has 0 parameters, so the schema provides no parameter semantics. The description doesn't need to explain parameters, but it does explain the meaning of the returned chip fields (key / label / count 人数) and the minCount behavior, which is the closest thing to parameter semantics for this tool. Baseline 4 for 0 params is appropriate; the description adds useful context about the data shape.

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 states a specific verb ('返回' / return) and resource ('真实可用的职业 chip（key / label / count 人数）'), and explicitly distinguishes it from list_talent by saying the chip values only come from here. It also names the sibling search_people as the alternative for semantic search. This is a clear, specific purpose that an agent can act on.

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 explicit when-to-use guidance ('要按职业扫人之前先调这一次'), tells the agent not to enumerate chips itself, warns against requesting /v1/ addresses (no outbound HTTP), and provides a full combination chain (get_talent_chips → list_talent → get_creator → start_conversation). It also explains when to use search_people instead. This is exemplary usage guidance.

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