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

Annotations only declare destructiveHint=false, so the description carries the real burden and does so: login is required, no deduplication happens server-side, and the phone-attribution rule (missing phone cannot attribute a later signup; claimedUserId non-empty means attributed) is spelled out. It even discloses a privacy behavior — only the last four digits of the phone are returned — which the agent cannot learn from any structured field.

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?

Front-loads login requirement and purpose, then the workflow chain, then caveats — good ordering with no filler sentences. The telegraphic phrasing (e.g. 已在站内且填手机则claimedUserId非空即归因) is dense enough that it takes a careful read, which slightly hurts scannability.

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 10-parameter mutation with no output schema, the description covers purpose, prerequisites, side effects, sibling routing, follow-up chain, and even the return shape (last four digits only). What it lacks is per-field semantics for the eight undocumented business fields, which is the main remaining gap for a tool of this 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?

Schema description coverage is 0% across 10 parameters, so the description must compensate, and it only really explains phone (pattern implied by the attribution discussion) plus the count of ten fields. Name, title, company, city, tags, note, wants, canOffer and wechat get no meaning, constraints, or intended use from the description; an agent cannot tell which of them drive matching or attribution.

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 and resource — 新增站外线索 (create an off-platform lead) — plus the notable detail that it supports ten fields, which matches the 10-property schema. It actively distinguishes itself from the sibling import_broker_leads, so an agent can tell create-vs-import apart without opening either 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?

Explicit when-to-use routing: single manual entry here versus batch/merging imports via import_broker_leads 按手机合并, and an explicit when-NOT-to-repeat warning (服务不去重，重调重复创建). It also gives the down-stream chain create_broker_lead → scan_broker_matches(leadIds=[id]) → create_broker_match, which tells the agent what to do immediately after success.

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