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

Annotations only declare the safety profile, but the description adds the real behavioral payload: idempotent retry via message_id, deterministic derivation that collapses identical text into ONE message, the already_received:true signal, and refusal conditions. That is substantial context beyond structured fields.

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?

Front-loaded with the core purpose and every sentence carries information, but it is one dense block with nested clauses and parentheticals (already_received, message_id derivation) that make it harder to scan than it needed to be.

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?

There is no output schema, so the description must cover returns, and it does: the unread-message count plus the pointer to get_turn for the rest, and already_received on the dedupe path. An agent has everything needed to call it correctly.

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 the baseline is 3, but the description goes further by explaining what message_id actually does: derived from caller/turn/words when omitted, and the escape hatch for a deliberate repeat. turn_id is tied to its source (send_message or get_chat), which the schema does not say.

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 first sentence states a precise verb and resource: hand a message to an agent WHILE a turn is running, and it names the sibling it is not (send_message as the next message). An agent can distinguish it from send_message, retry_turn and apply_turn without opening any schema.

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?

Explicit preconditions (only a running turn of a conversation you can message), explicit exclusion (refused once the turn has ended or already has messages waiting), and the named alternative (send_message) for that case. Nothing is left to inference.

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