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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=true, so "Read-only; changes nothing" restates what the agent already knows. What the description does add is domain context not in the structured fields: monetary values in the file appear as integer minor units (cents). It is silent on auth/sharing prerequisites for sheets and shopify sources and on what happens on an unreachable URL, both of which are real behaviors for an open-world fetch.

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?

Three short sentences, front-loaded with purpose and the pre-import ordering constraint. The middle sentence ("Read-only; changes nothing") is largely redundant with the readOnlyHint annotation, a small amount of wasted space in an otherwise tight definition.

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 low-parameter read tool with no output schema, the combined text covers what it does, that it mutates nothing, when to use it, and (via the schema description) what comes back: columns, sample rows, suggested field mapping, and XML repeating elements. Remaining gaps are edge behavior on fetch failures and sharing prerequisites, which are notable but secondary.

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% and the per-parameter docs are rich (enum meanings, the XML record example, the Shopify-still-online caveat), so the schema carries parameter meaning. The description adds only an indirect data-format note ("Money is integer minor units") rather than anything about how to choose source or record, so baseline 3 applies.

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 main sentence names a specific verb and resource ("Read a product file") and flags its pre-import role, and the schema description sharpens it further ("Fetch a supplier's CSV or XML file (or a Google Sheet) and say what is in it"). It stops short of naming the sibling it precedes by name in the top-level text, so an agent must read the schema description to distinguish it from imports_list or imports_run.

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?

"before importing it" plus the schema's "Use before imports.create" gives a clear trigger, and "use before" implies the ordering constraint that matters for a preview step. No explicit when-not case is stated (e.g. what to do if the file is already imported), which keeps it below a 5.

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