assemble_online_grocery_orderShopping list for the selected recipes minus ingredients on hand, grouped by item with quantities and which recipe needs it, plus the preferred store. Drive the browser to fill the cart; stop before checkout for approval; then call record_grocery_order.
| Name | Required | Description | Default |
|---|---|---|---|
| week_id | No |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full transparency burden and covers the most important side effect: it drives a browser, fills a cart, and deliberately stops for approval before checkout, so no order is placed. It does not disclose agent-facing non-observables such as permissions or failure behavior, but the approval boundary is a meaningful disclosure.
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 description is compact and front-loads what the shopping list contains before the browser steps. The two sentences carry no filler, though terms like 'selected recipes' are left somewhat implicit.
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?
The description explains the high-level workflow and the checkout boundary, but with no output schema, no annotations, and an unexplained week_id parameter, an agent lacks too much information about what triggers the final recording and what result to expect.
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?
The only parameter, week_id, has no schema description and is never mentioned in the tool description. At 0% schema description coverage, the description needed to explain how week_id affects 'selected recipes' but does not.
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 names a concrete resource ('grocery order/cart') and specific actions: compose a shopping list from selected recipes minus on-hand ingredients, then drive the browser to fill the cart. It also delineates the boundary with the sibling record_grocery_order by saying that tool should be called afterward.
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 provides clear context: use after recipes are selected, ingredients on hand are accounted for, a preferred store exists, and cart filling should stop before checkout. It doesn't list exclusions or explicitly contrast with other siblings, but the handoff to record_grocery_order is useful routing guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Most tools target a distinct resource and action, with detailed descriptions that clarify boundaries. The main confusable pair is run_agent_chef vs next_actions, which both return the due-action checklist and operating instructions, differing only by trigger context. propose_recipes vs add_candidates are also related but clearly separated by phase (initiating a cycle vs appending during feedback).
The overwhelming majority follow a verb_noun snake_case pattern (get_, update_, set_, add_, record_, remove_), which is highly predictable. Minor deviations include next_actions being a bare noun phrase rather than get_next_actions, and favorite_recipe using 'favorite' as a verb instead of something like toggle_favorite.
At 34 tools, the surface is heavy for an agent to select from, exceeding the 25+ threshold for 'too many'. The domain is genuinely broad, but several utility and meta tools (dismiss_setup_checklist, record_schedule, get_connected_agents, get_instructions) and overlapping entry points (run_agent_chef, next_actions) inflate the count and could be consolidated without losing capability.
The full weekly lifecycle is covered end-to-end: propose, vote, feedback, add candidates, lock in, shop, order, cook, rate, and mark done. Recipe, member, ingredient, and preference management all have solid get/update/create coverage. Minor gaps include no way to delete a recipe, remove a candidate from an active ballot, or cancel a week beyond reopen_voting, but these are work-aroundable and don't create dead ends.