update_attribute

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It discloses a critical limitation (type and logical name cannot be changed) and the recommended fallback. It also indirectly warns about potential failure (Dataverse will reject type changes). While it doesn't detail error responses or side effects, the key behavioral constraint is transparently communicated. A 4 reflects strong added context beyond the schema, with minor gaps around success/error behavior.

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: the first clearly states the core function and lists the updatable fields; the second adds a critical constraint and the alternative approach. Every sentence earns its place, and the most important information is front-loaded. No wasted words.

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 the tool's moderate-to-high complexity (14 parameters, 4 enums, no output schema, no annotations), the description combined with the rich schema provides a complete picture. The description explicitly covers the key limitation (immutable type/logical name) and alternative, while the schema documents every parameter with descriptions and constraints. There is no requirement to explain return values without an output schema. The description is appropriately sized and fully contextual.

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 100%, so the baseline is 3. The description lists several updatable parameters (display name, description, required level, max length, min/max value, precision) at a high level but does not add syntax or constraints beyond what the schema already provides. The schema's own parameter descriptions include important details (e.g., date_behavior one-way limitation, type must match existing), so the description adds little extra meaning. A 3 is appropriate given the schema's thoroughness.

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's purpose: updating metadata of an existing column, and enumerates the specific updatable fields (display name, description, required level, max length, min/max value, precision). It also distinguishes itself from sibling tools by explicitly noting that type and logical name cannot be changed, which separates it from add_attribute and delete_attribute.

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 explicit when-not-to-use guidance: for type or logical name changes, the tool is not appropriate, and the alternative workflow (create a new column, migrate data, then delete the old one) is given. It also references add_attribute for date_format semantics, reinforcing alternative usage. This is clear and actionable.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.