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

Goes well beyond the annotations (readOnlyHint=false, destructiveHint=false) by disclosing that nothing is sent, no number is assigned, the draft stays editable, it is deletable with one call, and it does not prompt for confirmation. It also mentions the return totals (net/tax/gross) and the auth requirement (Cotlet API key), which the annotations do not cover.

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?

It is front-loaded and mostly efficient, but repeats the same facts twice ('Nothing is sent and no number is assigned yet' vs 'has no invoice number, reaches no customer'), which is mild redundancy rather than pure economy.

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 the essentials: what it creates, that it is a safe non-sending draft, the return totals, the auth requirement, and the next step. Nothing critical for correct invocation is missing.

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 description coverage is 100%, so the schema already documents all six parameters including line-item structure. The description adds no additional parameter meaning, so baseline 3 is appropriate.

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 ('Save a draft invoice for a contact') and immediately scopes it as a draft, distinguishing it from finalize_document and send_document. An agent can tell what this does without opening the schema.

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 description positions this as the pre-finalization step and names finalize_document as the follow-up ('check them before finalize_document'), giving clear workflow context. It does not, however, spell out an explicit when-not-to-use condition or name a sibling for a different path.

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