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

Annotations already declare destructiveHint=true and idempotentHint=true, but the description adds materially more: deletion cascades to remove the field's value on every teammate, plus three concrete failure modes with HTTP codes. That is exactly the 'what gets destroyed and when it won't work' context the annotation cannot carry.

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 dense sentence with the verb and destruction scope front-loaded, followed by the failure cases. No filler, no restatement of the title, and every clause carries operational information.

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 destructive mutation with an output schema present and full annotation coverage, the description supplies the cascade semantics, addressing requirements, and complete error preamble. Nothing an agent needs before invoking it correctly is missing.

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 goes beyond the schema's 'id returned by list_smart_fields' by constraining which IDs are valid targets (custom fields only, not default or computed fields). It does not add anything further about the analytics-only context parameter, which is already fully documented.

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 ('Delete a custom smart field') with the addressing key (UUID) and immediately distinguishes it from sibling operations by noting it is a custom field. It also names what makes a field non-custom, so an agent knows update_smart_field/list_smart_fields are not substitutes.

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?

Explicitly enumerates the when-not conditions with status codes: default fields (422), computed Email field (404), fields in use by a signature template or campaign (409). These effectively tell an agent when the call will fail, though no alternative tool (e.g., update_smart_field) is named as a fallback.

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