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

Annotations already say read-only=false and destructive=false, but the description adds critical non-obvious behavior: it executes per lead and returns per-lead results, single failures do not abort the batch, and archived is archival rather than destructive. It also warns that including phone immediately binds the lead to a site user with irreversible first-come-first-served attribution, which is exactly the kind of behavioral context an agent needs.

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 structured into three focused sections: login requirement and batch behavior, the intended tool chain, and the caveats. Every sentence adds operational value, with the most important warnings clearly marked with ⚠.

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 two-parameter batch mutation tool with no output schema, the description covers auth, batching semantics, error behavior, patch semantics, side effects, and the recommended pipeline. The only thing not detailed is the exact result payload shape, but the description already states results are returned per lead and no output schema exists to specify further.

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?

Although the schema has 100% coverage, the description enriches the patch parameter substantially: it is one uniform patch applied to a batch, omitted fields keep their original values, archived=true is an archive operation, and phone has a dangerous binding side effect. This goes well beyond the raw JSON Schema property definitions.

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 opens with a specific action—'给一批线索打同一个 patch'—and names representative uses (补标签、补「在找什么」、批量归档) that map directly to patch fields tags, wants, and archived. This clearly distinguishes it from siblings like create_broker_lead, delete_broker_lead, and scan_broker_matches.

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 combination chain: list_broker_leads(q=…) to select leads → update_broker_lead(leadIds, patch) → scan_broker_matches, plus a clear intended-use statement that batch cleaning is the whole point. It also explicitly contrasts archived=true with deletion, telling agents when this tool is the right path for freeing quota.

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