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

Annotations already declare write, non-idempotent, non-destructive, open-world semantics. The description reinforces non-idempotency ('Each call creates another form'), clarifies the result is a draft, and states that assignment cannot be applied later — genuinely useful context beyond annotations. Return payload is not described, but no output schema exists and the create result shape is not critical to invocation correctness.

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?

Front-loaded with the WRITE verb and core action, then constraints. Dense but every clause (draft, assignment-only-at-creation, field key semantics, non-idempotent repetition) carries information. The trailing 'POST /v2/formz' is minor noise but harmless.

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 6-parameter write tool with nested objects and no output schema, the description covers the mutation effect, assignment timing constraint, and the trickiest part (field value shape). An agent can invoke it correctly. It stops short of describing the returned form id/reference, a minor gap given no output schema.

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% (baseline 3), and the description adds real value on top: field keys are template field names/ids, values are field objects like {"text": "Acme"}, plus a pointer to goformz_get_form for exact field shapes. This resolves ambiguity about the nested 'fields' object that the schema only loosely explains.

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 (create a new draft form from a template) with leading WRITE marker and scope qualifiers (draft, optionally pre-filled, optionally assigned). An agent can distinguish it from the read-only siblings like goformz_get_form and from goformz_update_form without opening schemas.

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?

Adds concrete context: assignment is only possible at creation, each call creates another form, and it points to goformz_get_form to learn field shapes before calling. It lacks an explicit 'use update_form instead when…' contrast, but the creation-vs-later distinction is clearly conveyed.

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