Set or update food preferences for a contact. Replaces all fields - pass all known preferences, not just changes.
| Name | Required | Description | Default |
|---|---|---|---|
| notes | No | Additional notes about food preferences | |
| allergies | No | Food allergies (e.g. ["peanuts", "shellfish"]) | |
| contact_id | Yes | The contact ID | |
| disliked_foods | No | Disliked foods | |
| favorite_foods | No | Favorite foods | |
| dietary_restrictions | No | Dietary restrictions (e.g. ["vegetarian", "gluten-free"]) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden. It discloses the critical behavior that all fields are replaced, preventing accidental data loss. It does not mention side effects like contact creation or return values, but the core overwrite risk is clearly communicated.
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?
Two sentences, front-loaded with the main action, and every word adds value. No redundancy 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?
The description adequately covers purpose, usage pattern, and an important behavioral trait for a moderately simple mutation tool. It could mention behavior for invalid contact_id or empty arrays, but for typical use the information is sufficient.
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 100% so the baseline is 3. The description adds semantic meaning beyond the schema by stating 'Replaces all fields', which clarifies that the parameter arrays (favorite_foods, allergies, etc.) are written as a complete set rather than merged or patched.
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 states the tool 'Set or update food preferences for a contact' with a specific verb (set/update) and resource (food preferences). It also distinguishes from its sibling food_preferences_get by implying a write operation, and highlights the key 'Replaces all fields' behavior.
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?
Provides explicit usage guidance: 'pass all known preferences, not just changes' tells the agent how to invoke the tool correctly for a full overwrite. However, it does not explicitly compare to alternative tools like food_preferences_get, so it lacks a clear when-not-to-use clause.
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 are clearly distinct by entity, but contact_get and contact_timeline overlap significantly, and debt_manage's action='list' duplicates what other entities do with a dedicated list tool. Descriptions are detailed enough to resolve most ambiguity, though.
Tool names are mostly snake_case and readable, but they mix conventions: noun_verb (contact_create), verb_noun (batch_create_activities), and descriptive phrases (contacts_needing_attention). The noun_manage pattern is dominant, but the lack of uniformity makes the naming less predictable.
With 42 tools, the surface is very large, even for a full-featured CRM. Many tools bundle multiple actions, but the sheer number forces an agent to consider many options, increasing selection difficulty and cognitive load.
The server provides comprehensive CRM coverage: contacts, activities, notes, tasks, reminders, gifts, debts, relationships, tags, custom fields, notifications, settings, and exports. It supports batch operations, duplicate detection, merge, and special queries, leaving few if any obvious gaps.