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

Annotations only cover read-only/no-open-world. The description adds real behavioral payload: service items return isService:true and onHand:null and must never be reported as a quantity, and Counter companies only reflect sales at day-close rather than per scan. These are non-obvious semantics an agent could easily get wrong.

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-loaded with the core answer, then two dense caveat sentences. Every sentence carries distinct information; the Counter explanation is niche but genuinely affects interpretation of the number.

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 explaining the return shape, and it does partially (isService, onHand). It does not describe the full field set or what happens on no-match, but the critical edge cases are covered.

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 0% and the single 'query' param is undocumented in the schema, but the description compensates by stating it accepts a product name or SKU, which is exactly what an agent needs to form the input.

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 resource (units on hand), a precise time scope ('right now'), and the retrieval key ('product name or SKU'). This cleanly separates it from sibling tools like stock_movements (history) and low_stock (threshold list) without needing to name them.

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?

It explains what the returned figure means and when a quantity is not applicable (service items, Counter day-close timing), which gives contextual usage. However, it never says when to prefer this over stock_movements or low_stock, nor any prerequisites, so routing guidance is only implied.

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