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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the description's restatement of read-only/idempotent adds little. It does, however, contribute genuinely new behavioral detail: the tool never raises a protocol error, instead returning an {"error": ...} object, plus example input/return shapes. That error contract is the kind of context annotations cannot carry.

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 purpose followed by example, scope, alternatives and error contract — a sensible order. Slightly long with inline JSON examples and the promotional 'FREE.' tag, but no sentence is truly wasted.

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?

Output schema exists so return values needn't be spelled out, annotations cover safety, and the description covers usage, error handling and retry safety. The one gap is that it omits how mode='update' tightens required columns, which is behaviorally relevant to interpreting missing_required.

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%, including the meaning of the new/update mode enum and the header_row format, so the schema already does the heavy lifting. The description adds a worked example of header_row but never mentions the mode parameter or how it changes what counts as a missing required column. Baseline 3 is appropriate.

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 — checking a product CSV's header row against Shopify's current columns — and names the exact failure it targets (stale template column names). It is also clearly distinguished from siblings like url_handle and metafield_key_check.

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 timing ('Use before an import, on the header row alone') and an explicit exclusion ('Not for whether the values in the rows are valid'), with named alternatives for the excluded cases. Nothing about tool selection is left to inference.

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