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

Annotations declare readOnlyHint=false, openWorldHint=true, idempotentHint=false and the description explains why: it invokes a billed model and requires login, so it is not side-effect free. It further discloses 429 rate-limit handling (must slow down), the one-full-site-search-per-anchor cost model, the merge/dedup behavior, and the candidate leadId=null → bUserId fallback. Rich context well beyond the annotations.

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 but every sentence earns its place: billing/login warning first, then matching semantics, then parameter tuning, then workflow chain, then edge case. Front-loaded with 【需要登录】 so the critical precondition is seen immediately.

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 2-parameter tool with no output schema, the description covers the preconditions (login), cost/rate-limit behavior, result semantics (merged, deduped, scored with reasons), downstream workflow, and the null-leadId edge case. Nothing an agent needs to call 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%, so both parameters are already documented (baseline 3). The description goes further by tying leadIds count to search cost (each anchor = one full-site search, max 8) and giving concrete perLead tuning guidance for pool vs. single hard-to-match cases.

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 (全池扫匹配 = full-pool match scan) and describes the core mechanic (merge private-pool + full-site candidates, cross-anchor dedup, keep highest score and all reasons). It explicitly positions itself between list_broker_leads and create_broker_match, so an agent can distinguish it from those siblings without opening any schema.

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?

Gives an explicit workflow: list_broker_leads → this tool → read candidates to user for confirmation → create_broker_match. It also says when to use many leadIds with small perLead (pool scanning) versus perLead=20 (hard-to-match single anchor), and adds a when-not by warning against loop-retrying.

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