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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so the safety profile is covered. The description adds genuinely non-derivable behavior: a hard cap of 20 results, a paid-only filter, and the omission of customer details from the payload — all useful for interpreting the output.

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?

One compact sentence that front-loads the resource and scope, then the returned fields and the caveat. No filler, nothing an agent has to scan past.

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 no-output-schema, single-parameter read tool this covers the essentials: what is returned, how many, and what is filtered out. Minor gaps remain — it doesn't say whether 20 is a ceiling that silently truncates or whether older orders are reachable elsewhere.

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?

Single optional parameter with 100% schema description coverage, so the schema already explains `project_id` and its fallback to the default workspace. The description adds nothing about it, which is acceptable at full coverage but earns only the baseline.

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 ('the store's 20 most recent paid Shopify orders') plus the fields returned (status, totals, line items) and one deliberate exclusion (customer details). It's clear what it returns but never differentiates itself from the sibling `list_orders` or from `shopify_get_report`, so an agent must infer the split.

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?

Usage is only implied: the fixed 20-item paid-only scope and the absence of any filter parameters signal 'quick recency peek' rather than a queryable list. There is no explicit when-to-use, no exclusion, and no pointer to the alternative `list_orders` or `shopify_get_report` tools.

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