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

Beyond the annotations (readOnlyHint=false, destructiveHint=false, idempotentHint=false), the description discloses non-obvious traits: every edit creates a new menuDraftId revision, unrelated dinners/locks/dietary rules/pantry choice are preserved, stale-edit errors return the current draft with changeApplied=false and support a partial retry, and undoLastChange does not touch Saved Weeks or prior shopping lists. None of this contradicts the annotations.

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 outcome and return value are front-loaded, and nearly every clause carries distinct operational information. The mid-section is a dense run-on enumeration of operations that would scan faster as a list, but there is little filler to cut.

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 15-parameter mutation tool with nested objects and an output schema, the description covers the remaining gaps an agent needs: revision semantics, preservation guarantees, error/retry behavior, auth gating and ID sourcing. Return-value details are left to the output schema, which is appropriate.

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 high (87%), so the baseline is 3, but the description adds real meaning: it maps parameter combinations to intents (slotId + replacementRecipeId also locks; reroll needs slotId; refillShortSlots takes no slotId; servings without a slot applies to the whole week; pantryMode/focusIngredients re-rank pantry) and warns that choices is atomic and must not be combined with other edits. A few parameters, such as focusIngredients and slotRequirement sub-fields, are left entirely to the schema.

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 ('Changes a menu draft and returns the updated draft with a new menuDraftId') and enumerates every supported operation (choice selection, reroll, refill, requirement change, servings, pantry, lock, undo). That makes it clearly distinguishable from siblings like create_weekly_menu, prepare_weekly_menu, save_menu and get_menu_draft, which it also references for slot IDs.

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 explicit routing rules: use refillShortSlots 'instead of rerolling short slots one by one' and only when slotIssues is non-empty; chooseForMe only on an explicit user request; chat-only changes leave the draft untouched. It also states the prerequisite boundary (choosing works before sign-in; saving/shopping needs a linked account) and points to get_menu_draft for exact IDs.

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