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

Annotations declare destructiveHint=true and readOnlyHint=false, which the description's mutation framing aligns with (no contradiction). Beyond the annotations, the description discloses the live-product refusal guardrail and the approval-tier semantics (from-now-on vs just-once approval, and the instruction not to re-ask in chat) — substantive behavioral context not available in the structured fields.

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 core scope and guardrail, followed by routing and approval guidance. Each sentence earns its place; only the approval paragraph is slightly verbose but it conveys actionable behavioral instructions.

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?

Complete for a mutation tool given the annotations carry the safety profile: it covers purpose, guardrails, approval behavior, and routing. No output schema exists, but the description does not need to explain return values. Minor gaps on field semantics are the only shortfall.

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 40%, and the description names the updatable fields (title, description, tags), partially compensating. However, it adds little beyond naming them — no format details (e.g., description_html being HTML) or guidance on whether fields are overwrite vs merge. The schema documents product_id and companyId, so the description's marginal value over schema is modest.

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 (update), resource (Shopify DRAFT product), and scope (title, description, or tags), and distinguishes itself from live-product editing by explicitly refusing ACTIVE products. This differentiates it from the sibling update_live_shopify_product without needing to open either 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 explicit when-to-use context ('building out or revising unpublished catalog'), an explicit exclusion ('Refuses live (ACTIVE) products'), and names the alternative ('the approval-gated live tool'). The routing line reinforces the draft-only scope, leaving nothing to inference.

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