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

Adds substantive behavior beyond the annotations: auth requirement, a shared 24h cap of 10 for INTRODUCED that backfills also consume, a 'read warning' instruction, and a no-deletion policy (mark DEAD instead). These are exactly the operational constraints annotations cannot express.

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 the login prerequisite and the core operation, then layers quota and error-handling facts compactly. Every clause carries a distinct rule, though the density makes it slightly harder to scan.

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 batch mutation tool with no output schema, the description covers auth, quota, non-deletion, and field semantics adequately. Return/result behavior is unspecified, but no output schema exists to cover it either.

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 the baseline is 3, but the description adds meaning by characterizing outcome/reason as the caller's own original-text ledger (本人原文账本) and by restating the status lifecycle. The enum list itself is redundant with the schema.

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 (批量改撮合状态/outcome = batch-update match status/outcome), which is enough to distinguish it from the create/introduce/scan siblings. The '批量' scope is clear, though it never names an adjacent sibling 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?

Gives real usage context: login required, record each item truthfully (逐项据实记录), and an explicit error-recovery rule ('建错改DEAD，不删除'). It stops short of naming when to prefer an alternative such as introduce_broker_match, but the INTRODUCED quota note hints at the boundary.

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