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

Beyond the annotations it discloses the traits that actually matter for a mutation: delivery lands "within seconds", the send "cannot be recalled", retries are safe via idempotency_key with same-key-returns-first-email semantics, and two named refusal modes (recipient_blocked, sender_not_ready). The idempotency explanation adds mechanism the idempotentHint flag alone does 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?

Five sentences, front-loaded with the send constraint and irreversibility before operational detail, and no filler. The merge-tag sentence largely restates the variables property description in the schema, a small redundancy that keeps it from a 5.

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 10-required-parameter, open-world mutation with no output schema, the description covers timing, irreversibility, retry safety and failure modes — the essentials. It does not say what a successful call returns (a send id usable with get_send or get_transactional_email), which would close the last gap given there is no output schema.

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?

With 70% schema coverage the baseline is already high, and the description still adds meaning: {{ variables.<key> }} merge-tag syntax for variables and the retry semantics of idempotency_key. It leaves to the schema the mutual exclusivity of html/markdown/template_id, which the schema documents anyway, so the gain is real but partial.

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?

"Send one email to one address now, for something the person did or asked for (a receipt, a login link, a notice), never marketing" names the verb, the resource, the cardinality, the timing and the triggering context in one sentence. The "never marketing" clause draws the line against the broadcast/campaign family in the sibling list, so an agent can route without opening a 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?

It states the trigger condition (user-initiated transactional message) and an explicit exclusion (never marketing), which is real when/when-not guidance. It stops short of naming the alternative tools for the excluded cases — create_broadcast or send_test_email would have made the routing unambiguous — so it falls just below a 5.

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