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

Beyond the annotations, it reveals login requirements, server-side automatic opener sending, the created/openerSent semantics, and that opener text is not returned when generated server-side. It also discloses the exact 429 behavior and directs the agent not to treat it as a transient failure.

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?

Although the description is long, it is well-organized into labeled sections, and every sentence carries operational weight. The formatting makes dense details like return semantics, quota rules, and related tools easy 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?

With no output schema, the description takes on the responsibility of explaining return values and does so thoroughly: conversation id, created, openerSent, opener/openerKind. It also covers quota errors, the exits payload, and related tools, making it complete for correct invocation.

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?

The input schema already fully describes both parameters, so the baseline is 3. The description adds useful context: peerUserId must come from get_creator/search_people, cannot be the agent's own user, and productId marks which product the conversation is about.

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 opens with a specific action: starting a 1-1 private conversation with a user, and immediately clarifies idempotency (returns existing conversation) and the optional productId. This clearly distinguishes it from siblings like get_conversation, send_message, and set_my_chat_opener.

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 explicitly tells the agent to obtain peerUserId via get_creator/search_people, forbids self-conversations, and explains quota consumption only applies to newly created conversations. It also gives a clear when-not-to-retry instruction for the 429 quota-exhausted case.

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