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

The description is otherwise rich, disclosing embedding cost, empty-result behavior, phone-number privacy pruning, and cloud-user contact restrictions. However, it explicitly states '不写任何数据' while the annotations declare readOnlyHint=false, which is a direct contradiction: an operation that writes no data is read-only. Per rubric, this caps the score at 1.

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 compact despite being detailed, with clear section headers and numbered operational caveats. It front-loads the decision rule ('何时用') and follow-up chain, and every sentence contributes practical guidance or behavioral context.

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 search tool with no output schema, the description covers routing, cost, privacy, empty-result fallback, cloud-user handling, and contact escalation. The only notable gap is that it does not spell out the exact response shape or item fields returned for each category, but the high-level behavior is complete enough for a capable agent.

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. The description adds meaningful usage semantics beyond the schema: scope=people|needs|products means 'view more' for a single category, the default per-category limits are 10/10/12, and phone-number queries cause people results to be empty. This goes beyond schema descriptions, though the schema still carries most parameter mechanics.

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 identifies search_all as a unified search that returns people, needs, and products in one parallel call, using a specific verb (search) and resource set. It also distinguishes this tool from single-category siblings by framing it as the default entry when the user's intent is ambiguous.

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?

Explicitly states when to use it: when a user asks one vague sentence and the agent cannot tell whether they want people, needs, or products. It also tells when NOT to use it (single category with long list → use scope=people|needs|products), gives a recommended follow-up chain, and warns against loop calls due to cost.

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