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

Annotations only declare non-readonly, non-destructive and open-world; the description adds real economic behavior: which column kinds are free versus paid, 0.02 credits per AI answer charged once per unique value, and how the first run interacts with connection day budget versus the list's own day limit. Nothing contradicts the annotations, and this cost disclosure is information the agent could not get from structured fields.

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 content is dense and mostly earns its place, but the structure is poor: it front-loads a garbled pricing clause ("FREE (key, Set up)", "Full on the list") instead of stating the action. Parenthetical asides make the single sentence hard to parse on first read.

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 nine-variant, nested-schema creation tool with no output schema, the definition covers cost, batching limits, and the setup prerequisite but says nothing about what the call returns (created column ids? the updated list?) or whether creation is immediate. It is usable but leaves the agent guessing at the result.

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 67% and the description adds genuine meaning to the `kind` discriminator by tying each kind to a cost model (AI criteria in score and ai_text are paid; the rest are free). The pointer to describe_setup also explains where the `field`/`op` values inside rules come from, which the schema only hints at. `list_id` and `language` are left to their schema descriptions.

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 never states plainly that it creates columns on a list; it opens directly into a free/paid eligibility table. However, enumerating the supported kinds (plain, select, formula, score, label, lookup, in_list, hubspot, job_change, ai_text) does let an agent infer the tool's domain. No differentiation from siblings like derive_column or remove_column.

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?

"call describe_setup first for the fields a rule may use" is a concrete prerequisite, and "Up to 10 columns per call" tells the agent how to batch. What is missing is any guidance on when to use this versus derive_column (which presumably also creates a computed column) or remove_column.

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