update_store_settings

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

Goes beyond the idempotentHint/openWorldHint annotations by disclosing real workflow behavior: guardrails 'escalate an otherwise-auto/confirm order to a pre-submission review', null explicitly disables a guardrail, and hold_channel_risk_review is ON by default and OVERRIDES fulfillment_mode including 'auto'. That override hierarchy is the kind of consequence an agent cannot get from structured fields. It still omits permission/authority requirements and whether changes apply to in-flight orders, keeping it shy of 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?

Front-loaded and front-loaded with the highest-value fact ('Only the fields you pass are changed'), then structured mode-by-mode. Dense but every sentence carries semantics for a 14-parameter tool. The trailing '[#fe3014]' artifact is stray noise that should not be there.

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 14-parameter mutation tool with no output schema and 100% schema coverage, this covers the non-obvious semantics: partial update, mode pipeline, guardrail escalation, and the default-on override. What is missing is peripheral but relevant context – required permissions/authority to change these settings, and whether changes affect already-open orders.

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 baseline is 3, but the description genuinely adds meaning the schema does not: the fulfillment_mode pipeline ('paid -> draft -> auto-confirm -> production'), the interaction between hold_* guardrails and the chosen mode, and the null-to-disable convention. That is substantive disambiguation of an enum plus 7 guardrail booleans rather than repetition.

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?

Specific verb+resource ('Update a store's fulfillment workflow / notification settings') that immediately separates it from the sibling read tool get_store_settings and from set_channel_settings. It also states the scope of what is editable rather than leaving the agent to infer it from 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?

It gives partial-update semantics ('Only the fields you pass are changed') and explains what each mode/guardrail means, which implies when to reach for it, but it never names an alternative or a when-not condition (e.g. use get_store_settings first to inspect current values, or set_channel_settings for channel-side config). Usage is implied rather than stated.

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