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

Adds real context beyond the annotations: the account must be connected, nothing is emailed and no invoice number is consumed at creation time, and delivery is a separate send_draft step. That is valuable given destructiveHint=true and idempotentHint=false, which on their own would suggest a riskier operation than creating a pending draft. It does not address duplicate drafts on repeated calls or what the returned draft contains.

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-loads the key constraint (creators only) and the no-send/no-number guarantee, then the fee. It is dense but every clause carries information, though the fee sentence is slightly tangential to the calling decision and the email-condition clause is grammatically tangled.

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 an 8-parameter nested tool with no output schema, it covers permissions, the draft lifecycle, error behavior, and the delivery handoff. Missing pieces are minor: what the draft response contains and whether re-invocation duplicates a draft.

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 75%, and the description still adds meaning the schema does not: client.email is the delivery target and its absence (with send_by email or both) produces needs_client_email, and send_by self emails nothing. It does not explain split versus deposit at the top level, leaving that guidance to the schema text.

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 ('Prepare an invoice to one of the creator's clients as a Draft') and pins the resulting state as a Draft rather than a sent invoice. It clearly separates itself from the send_draft sibling but says nothing about create_quote, so the quote-vs-invoice split is left to the name alone.

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 clear context: creators only, on their own account, and the draft becomes visible to the client only via send_draft after the creator approves. It also states the client.email precondition with the needs_client_email outcome. It stops short of naming create_quote as the alternative for pre-sale documents, and the deposit-vs-split choice is only covered inside the schema.

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