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

Annotations already declare destructiveHint=true, openWorldHint=true and idempotentHint=false, so the safety profile is partly covered. The description adds a real behavioral fact not present in the annotations: the operation blocks on owner approval before delivery, which materially affects how an agent should sequence the call. It still omits what happens if approval is denied or the invoice is already paid.

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?

Two short sentences, zero waste, with the action and channel options front-loaded and the approval caveat second.

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 mutating, approval-gated send tool with no output schema, the description covers the core action and the approval gate but leaves open the result shape (does it return pending?) and failure modes such as sending twice or sending on a paid invoice. Adequate but with clear 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 100%, so every parameter including defaults is documented in the schema. The description's channel phrasing ('email, text or both') loosely reinforces the two booleans but adds no format or combination rules beyond the schema, matching the baseline 3.

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 ... again') and enumerates channels, making clear this re-delivers an existing invoice rather than creating one. It does not explicitly distinguish itself from send_quote or list_invoices, so it stops short of a 5.

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 one crucial usage condition ('Waits for the owner's approval') and implies the invoice must already exist ('again'), but gives no explicit when-to-use/when-not guidance versus siblings like send_quote or how to obtain the invoice_id.

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