Add a column to an existing Microsoft Dataverse table by defining its logical name, data type, and display name. Use it to extend table schemas with fields like text, numbers, dates, or picklists.
Add a column (attribute) to an existing Dataverse table
| Name | Required | Description | Default |
|---|---|---|---|
| attribute | Yes | ||
| entity_logical_name | Yes | Logical name of the entity |
Changes observed during successful MCP inspections.
v0.9.0Input schema / $schemaPrevious value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"v0.7.1Input schema / properties / attribute / properties / global_option_setAdded value: +{
+ "description": "Picklist only: bind the column to an existing Global OptionSet by its set name (e.g. 'contoso_sourceset') so the column shares one org-wide list instead of a private copy. Mutually exclusive with options.",
+ "minLength": 1,
+ "type": "string"
+}Input schema / properties / attribute / properties / options / descriptionPrevious value: -"Options for Boolean (2 items: false=0, true=1) or Picklist types"New value: +"Options for Boolean (2 items: false=0, true=1) or Picklist types. Creates a Local OptionSet owned by this one column; mutually exclusive with global_option_set."v0.5.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are supplied, so the description carries the full behavioral burden, yet it only implies a write via the word 'Add'. It says nothing about required Dataverse privileges, that the new column is immediately persisted to the table's schema, or that some choices (e.g. DateTimeBehavior) are effectively irreversible.
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?
A single front-loaded sentence with zero waste. It is efficient, though its brevity is closer to under-specification than to disciplined conciseness, which caps it below a 5.
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 schema-mutating tool with a nested object parameter, no annotations and no output schema, the description omits permissions, side effects, error conditions, and any hint about how the required nested attribute fields must be combined. An agent cannot call this confidently from the description alone.
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?
Top-level schema coverage is only 50% (attribute has no description; entity_logical_name does), and the description contributes no parameter detail. However, the nested attribute object documents its own fields thoroughly, including mutual exclusivity of options vs global_option_set and defaults, so the schema largely does the heavy lifting.
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?
States a specific verb+resource ('Add a column (attribute) to an existing Dataverse table'), which maps cleanly onto the tool name and distinguishes it in kind from delete_attribute and update_attribute. It does not name or contrast those siblings explicitly, but the operation is unambiguous.
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?
No when-to-use guidance, no mention of prerequisites (the table must already exist, the attribute logical name must be unique), and no routing to alternatives such as update_attribute for modifying an existing column or add_picklist_option for extending a choice list.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.