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

Annotations already declare readOnly/idempotent/non-destructive, but the description adds genuinely non-obvious behavior: offset/limit slice a bounded, complete upstream response locally rather than paginating upstream, and only_toplevel is applied upstream. The escape hatch for oversized responses is also disclosed. It stops short of describing what the returned rows look like.

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 tight sentences with the core purpose front-loaded and no filler. The middle sentence is a fragment starting with a lowercase parameter name, which reads as shorthand rather than polished prose but costs little.

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 must convey what comes back; it names the quantities but not the row shape (location identifiers, fields per location) or whether pagination metadata is included. Combined with the unexplained required product_number, the agent has enough to call it but not enough to interpret the response confidently.

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 0%, so the description carries the full burden. It gives semantics for three of the four parameters (only_toplevel, offset, limit) but explains them in terms of placement (upstream vs local) rather than meaning — it never says what a 'toplevel' location is versus a sub-location, and product_number is not addressed at all.

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: read stock and available quantities for a single product broken out by warehouse location. The per-location scope distinguishes it cleanly from rackbeat_get_product and rackbeat_products, which cover product master data rather than stock distribution.

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: it tells you the tool is scoped to one product, and that very large responses require the Rackbeat dashboard, which is a useful fallback. But it never says when to prefer this over rackbeat_get_product or what preconditions exist (e.g., product must exist), leaving the agent to infer.

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