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

Annotations already flag destructiveHint=true, openWorldHint=true and non-idempotent, but the description adds the important non-obvious facts: delivery goes to the real customer, and a DRAFT invoice transitions to SENT — a state change an agent would not infer. It does not cover failure behavior, auth requirements, or whether resending is safe.

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 action, then logically grouped by platform, with no filler sentences. The dense semicolon-clause packing makes it a little harder to scan than it could be, but every clause carries real information.

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-parameter, destructive, no-output-schema tool with zero schema descriptions, the definition covers parameters, routing, defaults and the invoice state transition well. What it leaves unaddressed is error/failure handling and any prerequisite relationship between the invoice's customer and the recipient addresses.

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 carries the full burden — and it does: it explains `to` (with its two-level default), `cc` format, `subject` default, `email_account_id`, `chat_id`/`chat_uuid` sourcing, the invoice_id/invoice_uuid lookup, and how `message` is used differently per platform. Effectively all 10 parameters gain meaning beyond the bare 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 and resource ('Send an invoice ... to the customer') and enumerates the transport platforms, which distinguishes it cleanly from get_customer_invoice, list_customer_invoices and set_customer_invoice_status. The '[publish]' tag and 'Delivered to the real customer' further pin down what kind of action this is.

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?

Provides concrete invocation context per platform (email vs chat channels) and tells the agent where chat_id comes from (list_chats), plus defaulting rules for `to` and `subject`. It stops short of naming when NOT to use it or pointing to a sibling such as send_email as the alternative, so it is clear context but without exclusions.

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