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

Beyond idempotentHint/destructiveHint, it discloses that both sides' leads are set worked=true and that this affects 分账, that execution is per-item with failures not aborting the batch, and that duplicate pairs are treated symmetrically and idempotently. The worked=true side effect is exactly the kind of behavior an agent could not infer from annotations, and it does not conflict with destructiveHint=false.

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, confirmation and the 20-pair cap, then workflow, then semantics, then safety. Dense semicolon-chained clauses in one block make it slightly harder to scan than a short bulleted structure, but every clause carries operational information.

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 single-parameter batch mutation, it covers preconditions, ordering relative to siblings, per-item failure behavior, idempotency, side effects with billing impact, and content rules for reason. No output schema exists, but nothing needed to invoke this correctly is missing.

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 already 100%, yet the description adds meaning: bUserId is for in-site users not yet in the pool (service layer auto-collects first), and reason must be written in plain human language with no scores because it is shown verbatim on four ends. It omits goalId entirely, so it does not fully cover the payload.

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 (建撮合) plus batch scope (最多20对) and where it sits in the broker flow. An agent can tell instantly that this creates broker match pairs in bulk, distinct from scan_broker_matches (discovery) and introduce_broker_match (downstream action).

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?

Gives an explicit pipeline: scan_broker_matches → 用户确认 → 本工具 → get_broker_intro_scripts (off-platform send) / introduce_broker_match (in-platform group). It also names the precondition (user confirmation) and an expletive exclusion: 勿拿来试跑 because leads get marked worked=true and revenue split is affected.

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