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

Annotations already establish a safe read-only/idempotent profile, and the description adds genuinely non-obvious behavior: matches/attributions cap at 200 with no cursor, only counts/broughtInTotal stay full when truncated, contact info is masked to existence plus last 4 digits, and INTRODUCED backfill shares a 24h quota with group creation. These caveats materially affect how the agent interprets 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?

A single dense paragraph, front-loaded with the login requirement and the section inventory, with truncation and masking caveats following. Every clause carries operational meaning; only the quota sentence is somewhat tangential to invoking the tool.

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 an aggregated read tool with no output schema, the description covers the important quirks an agent needs: login, section scope, truncation semantics, and contact masking. The main residual gap is leadLimit behavior and any pagination guidance for the leads block.

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 67%; the description clarifies matchStatus's purpose (narrow the match scope) and the sections-to-blocks mapping implied by 总计/线索/撮合/归因, adding value beyond the schema. However leadLimit is undocumented in both schema and description, and the 200-cap mention is global rather than per-parameter, so it does not fully compensate.

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 resource and scope: the caller's own broker desk panorama covering totals, leads, matches, and attributions (本人撮合台总计、线索、撮合、归因). This aggregation framing implicitly distinguishes it from pure list tools like list_broker_leads, but no sibling is named explicitly, so it stops short of a 5.

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?

Provides a login prerequisite (【需要登录】) and tells the agent to use matchStatus to narrow scope, but never states when this overview should be chosen over list_broker_leads, list_broker_attributions, or scan_broker_matches. No alternatives or exclusions are given, leaving selection to inference.

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