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

Annotations already flag this as a non-idempotent, open-world write that is not destructive, so the bar is lower; the description adds genuinely new behavior beyond them — the 100-field account quota, the immutability of the type after creation, and a validation-only preview mode. It omits what happens on quota exhaustion and whether any permissions are required.

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 core action and its constraints are front-loaded in a single dense sentence, with the dry_run affordance last, so nothing is buried. The telegraphic semicolon style is efficient, though slightly clipped at the cost of readability.

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 four-parameter creation tool with full schema coverage and no output schema, the description covers the key things an agent needs: valid values, immutability, quota, and a safe preview path. It could still say what is returned (e.g., the created field object) and what error surfaces when the 100-field cap is hit.

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 all four parameters are already documented, including the 3-30 character name, the type enum, and its immutability. The description largely restates that (it repeats the length range and type options), so it adds little meaning the schema does not already carry — baseline 3.

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?

"Create a custom contact field (property)" pairs a specific verb with a specific resource and disambiguates the terminology (field = property), which lets an agent separate it from list_custom_fields, update_custom_field, and delete_custom_field without opening a schema.

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 gives concrete invocation guidance (dry_run: true to preview) and a usage boundary (accounts cap at 100 custom fields), plus "fixed once created" signals that post-creation changes must go through update_custom_field. It stops short of explicitly naming that sibling or stating preconditions for reaching the 100-field limit.

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