Register a new custom field on an object (contact/company/deal/activity). data_type: text|number|boolean|date|select|multiselect|currency|reference|email|url. Must be created before it can be written to a record.
| Name | Required | Description | Default |
|---|---|---|---|
| key | Yes | ||
| label | No | ||
| object | Yes | ||
| required | No | ||
| data_type | No | ||
| enum_group | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations provide only generic booleans (readOnly=false, destructive=false), so the description carries the burden of behavioral disclosure. It adds a key ordering constraint (must be created before writing) and enumerates valid data types, but does not describe duplicate-key behavior, permissions, or error handling, which would make it more transparent.
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 two sentences plus a compact data_type list, with no wasted words. It front-loads the core purpose and immediately provides the most crucial parameter constraint (data_type), earning its place.
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?
Given no output schema and minimal annotations, the description covers the core purpose, object types, data_type values, and a necessary prerequisite. But it omits semantics for enum_group and required, and does not mention the return value or error behavior for duplicate keys, leaving gaps for a 6-parameter tool.
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. It does for data_type by listing all allowed values and for object by listing valid targets, which is helpful. However, it leaves enum_group, required, key, and label to inference, so the compensation is only partial.
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 action ('Register') and resource ('custom field') with valid object types (contact/company/deal/activity), making it unambiguous. It distinguishes itself from sibling tools like relm_create_enum_value and relm_create_type, which handle other schema elements.
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?
The description provides a clear prerequisite ('Must be created before it can be written to a record') which guides when to use this tool. It does not explicitly name alternatives or exclusions, but the context of registering a field before record writing is clear enough.
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.
Every tool targets a distinct resource-action pair (e.g., create_automation, create_pipeline, create_template), and potential overlaps like batch vs create or log_activity vs create are clearly differentiated in descriptions. No two tools appear to do the same thing.
All 41 tools follow the relm_<verb>_<noun> pattern in snake_case, with conventional verbs like create, get, list, delete, manage, and restore. Minor plural/singular differences (list_automations vs get_automation) follow standard resource-naming practices and do not break consistency.
At 41 tools, the set is far beyond the 25+ threshold and feels heavy for an agent to navigate. While the CRM domain is broad, many tools could be consolidated (e.g., generic get/list by resource type) without losing clarity.
The tool set covers the full record lifecycle (CRUD, restore, batch, search) plus schema management, pipelines, stages, automations, sequences, templates, webhooks, channels, and usage. However, automations, sequences, and templates lack update operations—requiring delete-and-recreate workarounds—which is a minor but notable gap.
