Add Recipients

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

Annotations already flag destructiveHint=true and non-idempotent, but the description adds the operational consequence: the exact two-call dry-run pattern and the explicit IRREVERSIBLE label. That is behavior an agent cannot infer from the annotations alone.

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?

Two sentences: purpose first, then the required input source and the safety protocol in a bracketed callout. No filler, and the risky part is visually front-loaded.

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 3-param mutation with no output schema, the description covers prerequisites and the confirmation flow. It leaves out whether the mutation requires conversation-ownership permissions and whether added recipients see prior messages, both of which an agent might want before calling.

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 each parameter (confirm, recipients, conversation_id) is already documented with its source tool. The description only echoes the confirm dry-run semantics and the find_recipients source, adding no syntax or format detail beyond 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 (add), resource (recipients), and target scope (an existing Inbox conversation), plus the effect ('so they receive its messages'). This clearly separates it from send_message/reply_to_conversation, which create messages rather than modify membership.

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 the concrete prerequisite ('Get user IDs from find_recipients') and the confirm-then-execute protocol. It does not explicitly state the inverse case (use send_message for a new thread), so it stops just short of full alternative routing.

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