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

Annotations only say readOnly=false, destructiveHint=true, idempotent=false, openWorld=true; the description adds materially more — the result is a DRAFT that is not finalized until send_invoice, it is linked to the quote and its job, due dates derive from payment terms, and the part modes are plan-gated. That resolves the key ambiguity an agent would otherwise have about the destructiveHint and about whether the action is final.

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 and sized reasonably for a five-mode tool; nearly every clause carries information (mode semantics, pro gating, draft state). However, it is delivered as dense run-on sentences without list formatting, making the mode-by-mode semantics harder to scan than necessary.

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 mutation tool with no output schema, it covers preconditions, mode behavior, downstream finalization, and plan gating. The remaining gap is that it never says what comes back (e.g., the new draft invoice's ID), which the agent needs to chain into send_invoice — though the description implies linkage.

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?

The schema documents lines, amount, and quote_id (75% coverage) but leaves the required, behavior-defining `mode` enum undocumented; the description fills exactly that gap by defining all five modes and their interaction with the other parameters. It adds less for `lines`/`amount` since the schema already explains those, and adds the unstated rule "A part is one line at the quote's tax rate."

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?

Specific verb+resource ("Creates a draft invoice from a quote") plus an explicit anchor to the equivalent UI path ("as Create Invoice > From Quote does"). It also enumerates the five modes, so an agent can distinguish this from siblings like create_quote or send_invoice at a glance.

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 precondition ("from an approved or accepted quote"), describes what each mode is for, and points to send_invoice as the follow-up step. It also flags the plan requirement ("Needs a plan with progress invoicing (Pro) for the part modes"). It stops short of naming explicit exclusions versus other invoice-creation paths, so not a 5.

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