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

Annotations already declare non-destructive, non-idempotent, closed-world writes; the description adds real context beyond them: no external delivery occurs, the response contains an openUrl for user review, and a confirmation step should follow. It doesn't cover failure modes or what happens if a duplicate draft is created, which keeps it below a 5.

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?

Four short sentences, no filler, and the critical facts — what it does, the prerequisite, the no-send guarantee, and the review URL — are front-loaded. Every sentence carries distinct information.

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?

With no output schema, the description usefully discloses that the result includes an openUrl, and it defines the full workflow from contact lookup to send confirmation. Minor gaps remain around validation errors or duplicate-draft behavior, but nothing essential 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 coverage is 100%, so contactId, lines, dueDate, and notes are all documented in the schema itself. The description only restates the contactId provenance (lookup_contact), which the schema already says, and adds no line-item or dueDate semantics. Baseline 3 applies.

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 ("Create a draft invoice") and immediately clarifies scope with "Nothing is sent," which cleanly separates it from send_invoice and, by resource noun, from create_quote_draft. An agent can identify the operation 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?

Gives an explicit prerequisite sequence ("Call lookup_contact first to get the contactId") and a follow-up action ("afterwards ask whether to send it"). It stops short of naming an explicit alternative such as create_quote_draft for quotes, but the draft-versus-send distinction is made unambiguous.

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