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

Annotations already flag destructiveHint=true and readOnlyHint=false, and "corrects existing ones" is consistent with that, so no contradiction. However, the description does not warn that editing an existing food overwrites its stored values, nor does it say what happens on partial failure of the foods array or whether omitted fields are cleared — meaningful gaps for a destructive batch upsert.

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 front-loaded sentence with the create/edit split stated first and a compact colon list of covered fields. Slightly dense, but no filler sentences and nothing wasted.

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?

It covers what the tool writes but is silent on the array/batch behavior of the foods parameter and on what comes back (e.g., whether created food_ids are returned), which matters since there is no output schema. Adequate for a moderately complex mutation, but not fully complete.

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 the detailed per-100 vs. per-unit and create-vs-edit semantics are already carried by the schema. The description's phrasing ("unit", "the label's values per 100 g/ml and per unit") restates that framing without adding new meaning, so baseline 3 applies.

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 specific verbs and resource: creates foods in the person's catalog or corrects existing ones, and names the fields it handles. The create-vs-update duality is clear, though it never distinguishes itself from the sibling save_dish (food vs. dish), which an agent must infer.

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?

"Creates ... or corrects existing ones" implies the when: new food vs. editing an existing catalog entry. But it gives no explicit exclusion against save_dish, no statement about when to prefer logging over saving, and no prerequisites such as needing a food_id from list_foods (that only appears buried in the schema).

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