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

Beyond the destructiveHint/idempotentHint annotations, it discloses non-obvious behavior: top-ups are additive, only location-compatible items are topped up, ambiguous items return candidates while the rest of the batch still applies (partial success), staples like salt/pepper/oil are silently skipped, and a linked Chop It account is required. This is exactly the context annotations cannot carry.

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 verb and the three modes, then behavioral caveats in descending priority. The opening sentence is dense but each clause maps to a distinct operation; "Edits the same pantry the app shows" is the only mildly redundant line.

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?

Covers auth precondition, destructive/additive behavior, ambiguity resolution, and skip rules, which is everything needed before invoking a batch mutation. An output schema exists, so return-value explanation is rightly omitted.

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 the baseline is 3; the description goes beyond it by explaining location semantics (stock placed directly and only compatible items topped up) and by advising to omit unknown quantity/expiry rather than guess. It adds meaning rather than repeating field descriptions.

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 ("Updates the user's Chop It pantry") and enumerates the three operation families: add/top-up, remove by name, and change or delete exact rows by pantryItemId. The scope (the same pantry the app shows) makes it immediately distinguishable from the read-only sibling get_pantry.

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 condition-based guidance per mode: use add for bought/have items, remove names for used-up items, pantryItemId rows when precision is needed, and "read back before retrying a top-up, which is additive" warns against a common misuse. It does not explicitly name get_pantry as the read-back tool, so the alternative is implied rather than named.

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