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

Annotations cover the safety profile (destructive=true, idempotent=true, readOnly=false), so the description's job is to add context. It does: it discloses the side effects (recipient is notified, an invoice card is posted in chat), the automatic refusal of platform invoices, and an auth prerequisite. It does not contradict the destructiveHint=true annotation; it explains the outward-facing action.

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 sentences, zero filler, and the routing information is front-loaded: what it sends first, the refusal case second, the auth prerequisite last. Each sentence carries distinct decision-relevant content.

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 one-parameter mutation with no output schema and full annotation coverage, the description supplies everything an agent needs: the eligible invoice type, the side effects on the recipient and chat, the automatic-refusal exclusion, and the permission switch required to act.

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% for the single invoice_id parameter, so the baseline is 3. The description adds meaning beyond the schema by constraining the valid value to the member's own draft settle-privately invoices, matching the schema's note that drafts appear in my_invoices with status draft.

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 (Send) and a narrowly-scoped resource (one of the member's own DRAFT settle-privately invoices) plus the recipient. It explicitly carves out the sibling case — platform-generated booking invoices — so the agent can tell it apart from my_invoices and the automatic platform flow without opening any 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?

Gives explicit when-to-use (member's own drafted settle-privately invoice, drafts surfacing in my_invoices) and when-not (platform-generated booking invoices are refused because GigXchange sends them automatically). It also states the precondition — the member's "Allow my assistant to act" switch — which gates the call.

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