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

Annotations already flag destructiveHint=true, idempotentHint=false and a non-read-only write, so the safety profile is covered. The description adds real context beyond that: stock changes only through explicit calls, never as a side effect of meal logging. It stops short of stating what happens if quantity exceeds current stock, whether the item hits zero/negative, or whether the call is reversible.

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?

Two tight sentences, mutation and scope front-loaded, with the non-obvious no-silent-deduction rule as the follow-up. Nothing is redundant with the title or schema.

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?

For a destructive four-parameter mutation with no output schema, the description conveys the important behavioral model and trigger conditions. The remaining gap is outcome behavior — what the caller sees on success (remaining quantity?) and what happens when the requested quantity exceeds available stock.

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 75% and the unit and reason enums are documented in the schema itself, so the baseline is 3. The description only restates that a quantity is deducted from an item; it adds no guidance on defaulting units, when to pass reason, or how the quantity interacts with the item's own unit.

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?

"Deduct a quantity from a pantry item" is a specific verb plus resource, and the parenthetical scopes the trigger events. The second sentence explicitly separates this tool from joiva_log_meal / joiva_log_food, which an agent might otherwise assume mutate pantry stock.

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 conditions (after cooking, or when something was thrown away) and an implicit when-not (logging a meal). It never names the adjacent siblings an agent might confuse it with, such as joiva_update_pantry_item for a direct stock correction or joiva_remove_pantry_item for deleting the item entirely.

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