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

Annotations already flag destructive/openWorld/idempotent, and the description adds real substance on top: the auth handshake ('asks them to connect'), what actually happens on send (accept link for quotes, numbering plus pay link for invoices), and the concrete idempotency consequence ('Sending the same Draft again sends nothing'). That is materially more than the hints convey.

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 actor restriction and the core action, followed by outcome and guard clauses; every sentence carries information. Slightly dense in the parenthetical about connect and send_by self, which costs a bit of readability.

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 destructive, outward-facing action with no output schema, the description covers who may call it, auth requirements, side effects, and idempotency. The only gap is the unexplained 'send_by self' mode, which has no corresponding schema field.

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% and the single draft_id parameter is documented as the value returned by create_quote or create_invoice. The description adds only 'one Draft' of context, and it references a 'send_by self' mode that does not exist in this schema, so it neither compensates nor misleads at the parameter level.

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 ('Send one Draft to its client') and then spells out the divergent outcomes for a quote versus an invoice. This clearly separates it from the sibling creation tools create_quote and create_invoice, which make the objects rather than dispatch them.

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?

Explicit preconditions are given: creators only, on their own connected Piku account, and only after the creator has seen the Draft and approved sending. It also warns that re-sending is a no-op. It stops short of naming a sibling alternative (e.g., list_page_drafts to find the draft), so a 4 rather than 5.

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