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

Beyond the annotations (readOnlyHint=false, idempotentHint=true), the description discloses the 5,000-row cap, all-or-nothing semantics ('writes nothing while any row has a problem'), the per-row outcome vocabulary (create/update/unchanged/conflict), and that dry_run writes nothing. That is exactly the operational context an agent needs before a bulk mutation.

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?

Four sentences, front-loaded with purpose, then limits, then recommended workflow, then failure semantics and return shape. No filler and no repetition of schema text.

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?

No output schema exists, yet the description provides the return vocabulary the agent needs to interpret results, plus size limits and atomicity behavior. Nothing essential for a correct two-parameter bulk call is missing.

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 100%, so baseline is 3; the description adds value by explaining that each row carries the fields of create_product and by spelling out the intended dry_run-first workflow rather than just its type. It does not enumerate row-level required fields, which keeps it below 5.

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 with batch scope ('Add or update many products at once') and makes the upsert nature explicit, which distinguishes it from the singular create_product sibling. An agent can tell immediately what this does and that it is not a single-record call.

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 a concrete workflow rule — 'Send `dry_run: true` first' — and defines the failure/validation protocol. It does not name siblings such as create_product, get_import_template_columns or list_products as alternatives for other cases, so routing is implied rather than explicit.

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