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

Annotations already declare readOnlyHint=false, destructiveHint=false and openWorldHint=true, so the write/non-destructive profile is covered. The description adds genuinely new behavioral context: the result is a draft (reversible, not sent), it can be run 'without asking first', and it needs a Cotlet API key with access to the app. It does not describe the return value, but the added state and auth details are meaningful.

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?

The purpose is front-loaded and the mode semantics are packed into one dense sentence. There is mild redundancy between the title echo and 'Creates a draft invoice from an accepted quote', and the trailing API key note reads as an afterthought, but overall little space is wasted.

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 non-destructive draft-creation tool with no output schema, the description supplies enough to call it correctly: the required quote source, the mode mechanics, and the draft-until-sent lifecycle. It could note what the created draft returns (e.g., invoice ID) or that quote_id comes from list_quotes, but the essential context is present.

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%, so the baseline is 3, but the description goes beyond the terse enum list by explaining what each mode does ('entire invoices everything, remaining invoices what is not yet invoiced, percentage and fixed_amount take amount, and line_items picks lines'). That is real semantic value over the schema, though the amount format itself is left to the schema field description.

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?

The description gives a specific verb+resource ('Draft invoice from an accepted quote') and clearly frames the scope ('for all of it or part of it'), which an agent can distinguish from trade siblings like send_invoice and create_quote. The first two sentences restate each other almost verbatim, which slightly dulls the front-loading but does not obscure the purpose.

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 establishes the context of use (an accepted quote, whole or partial) and routes the agent by noting the invoice 'stays a draft until send_invoice', implying send_invoice is the follow-up step. It does not explicitly name alternatives or exclusions (e.g., when to use create_quote instead), so it stops short of full when/when-not guidance.

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