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

Annotations already declare destructiveHint=true, idempotentHint=true and openWorldHint=true, so the safety profile is largely given. The description usefully spells out what idempotency means in practice ('Retrying with the same idempotency_key returns the first result'), which is real added value. However, it never warns about the destructive/irreversible external-send nature, recipient restrictions, or what happens to a partially failed send.

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?

Three compact sentences, each carrying a distinct rule, with the mode-selection rule (thread vs. reply) front-loaded. No filler or repetition of the schema.

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?

The core routing rule and idempotency semantics are present, which covers the most common failure modes. But for a destructive, open-world mutation with eight parameters and no output schema, the description omits return-value expectations (message id, thread id) and permission/recipient constraints, leaving meaningful gaps.

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 description coverage is 0%, so the description must carry parameter meaning, and it only covers to_addresses, thread_id, subject, and idempotency_key indirectly. Four of the eight properties (text, reply_to, satisfied, as_address beyond the phrase 'one of your addresses') remain undefined anywhere. Partial compensation warrants a middle score.

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 concrete verb and resource ('Send a message as one of your addresses') and immediately clarifies the two send modes (new thread vs. reply). It is distinguishable from read-side siblings such as check_messages or read_thread by the explicit 'send' framing, though it never names an alternative tool.

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?

Offers real conditional guidance: to_addresses starts a thread, thread_id replies in one, and subject is only valid with to_addresses. That resolves the main ambiguity an agent would face. It stops short of stating when *not* to use this tool or what happens if both thread_id and to_addresses are supplied.

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