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

Only idempotentHint is supplied, and the description still discloses the key traits: the send is irreversible ("发出去收不回"), a 3-person group is created, login is required, there is a rate limit of 10 per rolling 24h shared with update_broker_match INTRODUCED backfill, and an already-introduced match returns the original conversation without consuming quota. That already-introduced-returns-original behavior is consistent with idempotentHint rather than contradicting it. The only real gap is that it doesn't say what the confirmation/return payload looks like, which is minor without an output schema.

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?

Every clause carries information — irreversibility, confirmation step, platform scope, quota, idempotent return, message finalization, call order — and the highest-risk warning is front-loaded with a ⚠ marker. It is dense semicolon-chained prose rather than visually structured sections, so it is slightly harder to scan than it could be, but nothing is filler.

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 2-parameter side-effecting tool with no output schema and minimal annotations, the description covers everything an agent needs: preconditions, confirmation protocol, quota and its interaction with a sibling tool, the already-introduced short-circuit, and the surrounding workflow. An agent can invoke this correctly and safely from the description alone.

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 matchId and message are already documented, which sets the baseline at 3. The description adds genuine meaning beyond the schema for the optional message parameter: it must be self-finalized, must be read back to the user for confirmation, and if omitted the system will send the match reason or a default line. That is real behavioral semantics, not repetition.

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 states a precise verb and effect: it creates a three-person group between A and B and sends the first message in the user's own name, pushing it to both parties. "真发" is disambiguated as an actual side-effecting send, and the description explicitly separates this tool from get_broker_intro_scripts (off-platform), create_broker_match (upstream creation) and send_message (downstream).

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 names the precondition (both parties on-platform) and the explicit alternative for the failure case (off-platform → get_broker_intro_scripts, send it yourself). It also gives the exact call order create_broker_match → get_broker_intro_scripts → confirm → this tool → send_message, and forbids batching ("单条执行，不批量"), leaving nothing to inference.

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