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

Beyond annotations, it discloses that the action is irreversible, requires login, notifies real users, must be confirmed with the user beforehand, is limited to single operations, shares a daily quota with update_broker_match, and returns alreadyIntroduced=true on duplicates. These are material behavioral traits that annotations alone do not convey.

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 description is dense but well-organized into labeled sections (safety warning, policy bullets, combination chain), with the critical warning front-loaded. Every sentence carries operational information; no 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?

Given the tool's high stakes and no output schema, the description covers all essential context: prerequisites, alternative routing, quota, idempotency, message fallback behavior, and the exact workflow. An agent has enough to invoke it correctly and safely.

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 already describes both parameters fully. The description adds practical semantics: message is sent in the user's name, must be read back for confirmation, and falls back to a match reason or a dry default if omitted — with an explicit warning not to use the default. This meaningfully enriches parameter understanding.

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?

Description states a specific verb and resource: it really creates a three-person group named `A × B` and sends a first message in the user's name to two real people. This clearly differentiates it from related tools like get_broker_intro_scripts and update_broker_match.

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?

Explicitly states when to use (both parties are in-site users), when not to (if a party is external, use get_broker_intro_scripts instead), and provides the full combination chain create_broker_match → get_broker_intro_scripts → introduce_broker_match → send_message. Quota rules and safe-retry behavior are also spelled out.

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