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

Goes well beyond the annotations by disclosing atomicity ("All-or-nothing, if any email is invalid none are sent"), the whole-batch blast radius of paused-tenant and tenant-cap errors, and the required key scopes (`sending_access` or `full_access`). These are exactly the failure-mode facts an agent needs before committing a 100-message call.

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?

Four short, front-loaded statements: capability and limit, atomicity/error scope, supported features, then alternative and auth. No sentence is filler.

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 still doesn't say what comes back (e.g., per-email ids or a partial-failure report), which matters for a tool whose all-or-nothing contract is its selling point. Everything else an agent needs to call it correctly is present.

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; the description adds real value by telling the agent to put the emails in `body` as an array and that attachments, `scheduled_at`, and a per-email `tenant_id` are supported at the item level. It doesn't mention `idempotency_key`, the one top-level parameter whose retry semantics matter most.

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 and resource ("Send batch emails") and immediately bounds the scope with "Sends up to 100 emails in one call." The final guidance to prefer send_email for a single message cleanly separates it from the nearest sibling.

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?

Explicitly routes single-message use to send_email and implies this tool is for bulk fan-out. It doesn't spell out when a broadcast (create_broadcast/send_broadcast) would be the better choice, which is the one remaining sibling ambiguity.

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