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

Annotations already declare idempotentHint=true, destructiveHint=true and readOnlyHint=false, so the safety profile is covered. The description adds return contents (previous and new quantity) and that the value replaces rather than adds, but it omits the optimistic-concurrency refusal and the destructive nature of overwriting a prior count, both of which live only in the schema.

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 short sentences with zero filler, front-loaded with the usage trigger before the behavioral detail. Tight and readable, though the return-value sentence could be trimmed since an output schema exists.

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?

Complete for a three-parameter mutation: purpose, exclusion, replace semantics and return shape are all stated, and an output schema covers return values. A note about the concurrency check failing or about permission requirements would close the remaining gap for a destructive write.

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 100%, so all three parameters, including the expectedLastEditTime guard and id format, are documented in the schema. The description reinforces replace-not-add semantics for quantity but adds nothing beyond the schema text, making the baseline 3 appropriate.

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 ('correct or update how much of an item a business has in stock') plus the triggering situations (after a count or a delivery). It also explicitly excludes the adjacent create operation, so an agent can separate it from list_inventory_items and from item creation.

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 clear when-to-use context ('when someone asks to correct or update... after a count or a delivery') and a when-not condition ('Not for adding a new stock item'). It does not name a concrete alternative tool, since the create counterpart is not in the sibling list, but the exclusion still routes the agent away from a wrong write.

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