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

Goes well beyond the annotations by disclosing rate limits (20 emails/hour per person, one per document per 10 minutes), plan allowance caps, the unconfirmed-address failure code, and free-plan restrictions on links. The destructive, non-read-only nature implied by annotations is reinforced with concrete consequences.

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?

Dense but front-loaded with the core action and side effects, then constraints. Every sentence carries operational information (limits, confirm rule, plan restrictions) with little filler, though the block is long.

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 7-param mutation tool with no output schema, the description covers the action, side effects, rate limits, plan gating, confirmation flow, and failure mode. An agent has everything needed to call it correctly.

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 already 86%, but the description adds real meaning: `to` must be a single plain address, `amount` must equal the total or nothing happens, and `confirm: true` is what distinguishes preview from execution. Adds value beyond the schema descriptions.

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 (emails the document to the client on the user's behalf, replies go to the user) plus the concrete side effects (draft takes next number, becomes sent, link published). This distinguishes it from a plain send_invoice status change and clearly identifies the email action.

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?

The two-step workflow is spelled out: needs confirm: true and an amount equal to the total, otherwise you get a preview. It also explains when to use the document's own address versus `to`. It does not explicitly contrast with siblings like send_invoice or get_invoice_email_draft, so it falls short of a full routing statement.

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