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

Far beyond the annotations, it discloses per-item receipts, no rollback on partial failure ('部分失败不回滚'), that omitted fields stay unchanged, that 'archived' only archives while retaining record/attribution and releasing pool quota, and that a phone change instantly binds to an in-app user with first-come-first-served, irreversible attribution. This is exactly the risk context an agent needs before a batch mutation; the 'irreversible attribution' warning sits in mild tension with destructiveHint=false but does not contradict it, since no data is deleted.

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?

It is dense, semicolon-delimited, and front-loaded with the action, and every clause carries actionable content (auth requirement, failure mode, field semantics, precondition, alternative tool). The telegraphic style is slightly cryptic for non-native readers, but nothing is redundant.

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 two parameters, a nested patch object, and no output schema, the description covers the parts that matter: partial-failure behavior, patch semantics, and irreversible side effects. It does not describe the shape of the per-item receipt response, which is the one remaining gap for an agent parsing results.

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 real meaning for two fields the schema cannot express: '省略不改' (omitted = unchanged, a partial-patch contract) and the special semantics of 'archived' and 'phone'. Other patch fields (name, tags, note, etc.) get no extra semantics because their JSON Schema constraints already speak for themselves.

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 names a specific verb and resource ('批量patch本人线索' – batch patch of the caller's own leads) and fixes the scope to the caller's own records. This clearly separates it from create_broker_lead and update_broker_match, which handle a single lead or a match, without needing the 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?

It gives an explicit prerequisite workflow ('list_broker_leads先挑人' – use list_broker_leads to select people first) and a hard precondition ('须先确认改前/后号码' – confirm old/new numbers before changing phone). It does not state when to prefer a single-record update path over this batch path, so alternatives are only partly covered.

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