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

Annotations already declare readOnlyHint=true and destructiveHint=false, so safety is covered. The description adds genuine behavioral detail the annotations cannot: the identifier precedence rule and the no-identifier fallback to a paginated listing, plus the underlying GET /products_stock route. It says nothing about pagination shape, behavior when an identifier matches nothing, or whether stock is per-warehouse.

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?

A single dense sentence that front-loads the primary case (one product) before the fallback (all products), with no filler. The parenthetical precedence clause is information-dense but slightly run-on; still, every clause earns its place.

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, and it only says "stock quantity" or "a page of stock levels" without indicating the fields in a stock entry or whether quantities are broken out per warehouse (notable given the sibling sellasist_list_warehouses). Adequate to call correctly, but thin for interpreting results.

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, but the description adds meaning the schema does not encode: the mutual-exclusivity/precedence ordering among id, ean, symbol and catalog_number ("the first one given in that order counts"). That directly changes how an agent should fill these parameters. Limits/offset semantics are left entirely to the schema.

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 concrete resource (stock quantity) and verb (get), and distinguishes its two modes: single-product lookup by identifier vs. a paginated listing of all products. It does not explicitly differentiate itself from siblings like sellasist_get_product or sellasist_list_products, so the agent must infer that this tool is stock-specific.

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 clear rule for selecting between the two modes: any of id/ean/symbol/catalog_number yields one product, none yields a page. It also specifies a precedence order among identifiers, which is real usage guidance. It stops short of naming alternatives (e.g. use sellasist_get_product for full product data) or exclusions, so it lands at 4 rather than 5.

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