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

Annotations already declare idempotentHint=true and destructiveHint=false, so the baseline is low; the description still adds real behavior: archived leads are restored rather than duplicated, self or unavailable accounts land in 'skipped' without aborting the batch, and anonymous signups are skipped and counted. These partial-failure and state-restoration semantics are not derivable from the annotations or schema and materially change how an agent should interpret results.

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?

Every clause carries information — limits, idempotency, restore, skip behavior, content restrictions, next step — and the action plus the 20-item cap are front-loaded. Density comes at a cost: semicolon-chained fragments with no spacing make it slower to parse than necessary, though 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?

For a 3-parameter mutation with no output schema, the description covers nearly everything an agent needs: auth prerequisite, batch cap, per-item skip semantics with reported counts, idempotency/restore behavior, and the natural next tool. It stops short of describing the exact shape of the result (e.g. collected vs. skipped counts and any per-lead identifiers), which an agent would still have to discover.

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 a 3 is the floor, and the description earns above it: it constrains note content (no questionnaire answers), constrains tags to activity markers only, and defines the eligibility rule for userIds (only signup entries with a userId, anonymous skipped). That is semantic policy the schema cannot express.

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 states a specific verb and resource: batch-collect up to 20 on-site users into the caller's own lead pool, with the limit spelled out inline. It never names the adjacent siblings (create_broker_lead for a single lead, import_broker_leads for file imports), so an agent must infer the difference from the verb '收' plus the userIds array rather than being routed explicitly.

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 concrete operating context: requires login, applies to signup lists where only entries carrying a userId are taken, and points to scan_broker_matches as the follow-up step. It also issues a hard prohibition (do not copy questionnaire answers into note), which is genuine usage guidance. What is missing is an explicit statement of when to prefer this over create_broker_lead or import_broker_leads.

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