create_test_outbound_mail

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

The description discloses key behaviors beyond annotations: always test_mode=true, cost_cents=0, includes estimated_live_cost_cents and cost_breakdown, and queues a mail.submitted webhook. Annotations only indicate non-readonly, non-destructive, non-idempotent, so the description adds significant behavioral context.

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?

Two sentences: first clearly states purpose, second adds key behaviors and usage context. No redundant wording; every sentence earns its place.

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?

Given the tool's 10 optional parameters, nested objects, and output schema, the description covers core behavior (test-only, estimates, webhook) and usage context (sandbox rehearsal). It's sufficiently complete for the AI agent.

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 baseline is 3. The description adds value by explaining the overall effect of parameters (e.g., simulation for pricing, live estimates) beyond individual field descriptions. It does not detail each param but contextualizes them well.

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 explicitly states the tool creates a sandbox outbound mail record without uploading a real document. It distinguishes itself from sibling tools like send_outbound_mail (real mail) and advance_test_outbound_mail (state progression) by focusing on simulated creation.

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 advises using it with a sandbox key to rehearse workflows before real sending. While it doesn't explicitly list when not to use it or compare to all siblings, it provides clear context for appropriate usage.

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