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

None of the annotations reveal the side effects spelled out here: replacing ingredients recomputes totals, setting top-level numbers rescales the ingredient breakdown proportionally, editing a routine-created log's title or calories mutates the saved routine, and changing logged_time can re-infer the meal. These are exactly the non-obvious mutation consequences an agent needs before calling a destructive tool.

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?

The mode-selection rule and prerequisite are front-loaded and each sentence carries distinct operational information. It is dense — long sentences with parentheticals and capitalized emphasis — but little is genuinely removable given the two-mode semantics being described.

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, side-effect-heavy mutation tool with no output schema, the description covers prerequisites, the two exclusive modes, side effects on saved routines, meal re-inference, and auth requirements. Nothing an agent needs to call it correctly appears to be missing.

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 only 25%, so the description carries the burden, and it does: it explains the mutual exclusivity of `ingredients` vs top-level numerics, that values are absolute rather than deltas, that ingredient names/amounts are preserved under rescaling, and that logged_time is time-of-day only. It doesn't cover the individual nutrient fields or their bounds, though the schema supplies those directly.

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?

The description opens with a specific verb and resource ("Correct an existing FOOD log") and immediately enumerates the editable facets (title, nutrition numbers, ingredient list, meal, time-of-day). It also scopes the tool to FOOD items, which separates it from the sibling log_exercise/log_water/log_weight tools.

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 gives an explicit prerequisite ("Read get_today/get_day first"), names the exact source of the id (`recent`, type "food"), and lays out the decision rule between the two modes: send `ingredients` when composition changed, top-level numbers when only totals changed. It also states the constraint "edit one log at a time" and the token requirement.

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