search_recipesEvery recipe the household has ever had proposed, with ratings and cook counts. Filter by text, favorites, or tag. Use recipe_id from here with propose_recipes to re-propose.
| Name | Required | Description | Default |
|---|---|---|---|
| tag | No | ||
| query | No | ||
| favorites_only | 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 provided, the description carries the behavioral burden. It discloses that the search covers all proposed recipes, supports filtering by text/favorites/tag, and returns ratings and cook counts. It does not mention ordering or pagination, but for a read-only search tool the disclosed behavior is sufficient.
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, with three purposeful sentences: scope and result contents, available filters, and downstream use of recipe_id. Every sentence contributes actionable information without repetition or filler.
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 simple search tool with no output schema, the description covers the search scope, filter options, key result fields, and a downstream workflow. It does not specify the full return shape or edge cases, but the essentials for correct invocation are present.
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 0%, so the description must compensate. The phrase 'Filter by text, favorites, or tag' maps directly to the query, favorites_only, and tag parameters, giving each parameter meaningful intent. It does not detail exact matching semantics, but the mapping is clear enough for optional filters.
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 clearly identifies a search action over the household recipe library and defines the searchable scope: every recipe ever proposed. It also distinguishes itself from narrower siblings like get_recipe or get_favorite_recipes by covering the full library and including ratings and cook counts.
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 clear operational context by explaining that recipe_id from these results can be used with propose_recipes to re-propose a recipe. It does not explicitly contrast against sibling tools like get_favorite_recipes, so it stops short of a full when-to-use versus alternatives statement.
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.