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

readOnlyHint=true is already supplied, but the description adds real behavioral context: output contains no contact details, scripts cannot be sent on the user's behalf, and a completed introduction consumes the 24h group-creation quota. The 'bothPlatform=true' condition is described as a gate even though no such input exists, which muddies the operational picture somewhat.

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 information is front-loaded and dense, but it is written as a semicolon-chained run-on that mixes this tool's behavior with instructions for two other tools. The bothPlatform clause is not just extra length, it is misleading length.

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 one-parameter read tool with no output schema, the description covers the essentials (script count cap, absence of contact info, non-proxy sending rule). However, it never describes what a script entry actually looks like or how to use the returned text, and the phantom bothPlatform parameter leaves the agent with an incorrect mental model of the call.

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% and the single matchIds array is fully documented (min/max items, id constraints), so the description need only stay consistent. Instead it references a 'bothPlatform=true' flag that does not exist in the schema (additionalProperties: false), which would lead an agent to pass an invalid argument. The '最多20条' restatement adds nothing beyond maxItems: 20.

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 names the resource precisely: up to 20 matchmaking intro scripts ('最多20条撮合的介绍文案') for given match ids, with the important qualifier that no contact info is included. It implicitly separates itself from siblings by naming introduce_broker_match and update_broker_match as downstream steps. It lacks an explicit verb ('retrieve'), which is why it falls short of 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?

Strong workflow routing: off-platform sending must be done by the user themselves ('站外必须交用户本人发，不代发'), in-site group creation goes through introduce_broker_match, and completed introductions must be logged via update_broker_match(INTRODUCED). What is missing is guidance on when to call this tool versus e.g. scan_broker_matches or get_broker_desk to obtain the match ids.

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