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

Annotations already declare readOnlyHint=true and destructiveHint=false; the description reinforces this with 'Read-only' and explicitly redirects mutation intent to three sibling tools, which is genuinely useful routing context. It also discloses result ordering and the aggregate low/out counts. It stops short of covering pagination or how the row cap behaves when more items match than are returned.

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-loads the resource, scope, and sort order in the first clause, then layers filters, examples, and alternatives in a logical progression. It is dense rather than padded, though the multilingual example parenthetical and the list of sample questions push it slightly longer than strictly necessary.

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?

With no output schema, the description carries the burden of return shape and does so by naming the per-row fields (on hand, reserved, available) and the company-wide counts. Combined with annotations, an agent has enough to call it correctly; only the limit/pagination behavior is left unaddressed.

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 67%, and the description compensates well for the two documented params: it explains status='out'/'low' semantics beyond the enum labels and clarifies that search matches item name OR number with word-stem matching (with a non-English example), which the schema does not say. The 'limit' parameter, which has no schema description, is never mentioned in the description, leaving one param unexplained.

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?

Opens with a specific verb/resource statement: warehouse stock from the ERP, per item and warehouse, with quantity on hand, reserved, and available, plus company-wide low/out-of-stock counts. The ordering rule ('EMPTIEST rows first') and the example questions make the resource unmistakable and clearly distinguishable from the mutation siblings.

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 explicit routing: use status='out'/'low' to see only what needs ordering, use search for a single item, and enumerates the natural-language questions it answers. It also names the alternatives for write paths (erp_stock_adjust for add/write-off, erp_stock_recount for counts, purchase_invoice_receive for supplier receipts), so an agent knows when NOT to use this tool.

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