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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint false, and the description goes well beyond them: it reveals that professions are machine-classified, that chip availability depends on a server-side threshold, that unknown chips default to 'all' without error, that results are real users only, that no contact details are returned, and that nextCursor is just the next offset. This is rich behavioral disclosure with no contradiction.

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 long but tightly organized into clearly labeled sections — when to use, sibling differences, chaining, and pitfalls. Every sentence carries either a usage rule, a behavioral caveat, or a downstream routing hint. No filler or repetition; the structure makes dense content 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?

With no output schema, the description carries the burden of explaining the response shape, and it does: it references items[].user.id, items[].company.slug, items[].professions, and nextCursor. It also explains edge cases like sparse chips returning zero results, pagination limits, and the absence of contact info. An agent has enough context to call and interpret this tool 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 100%, so the baseline is 3, but the description adds substantial semantic value beyond the schema: chip is a merged bucket vs fine-grained profession labels, the actual chip set is determined by GET /v1/talent/chips, unrecognized chip keys are treated as 'all', and offset pagination is explained with nextCursor semantics. The description fully compensates and more.

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 clearly states this tool lists people by profession, not products/services, and uses concrete user examples like '帮我找个能写代码的'. It explicitly distinguishes itself from list_service_products and search_people, making the tool's scope unmistakable.

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 with real-world prompts, contrasts against list_service_products ('he sells what' vs 'he is what'), and against search_people (semantic search vs structured category browsing). It also tells the agent to use search_people when a person has no detected profession, which is a valuable exclusion rule.

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