Add a linear numeric scale question to a Google Form, specifying low/high values, labels, and required status to capture rating responses.
Add a linear numeric scale.
| Name | Required | Description | Default |
|---|---|---|---|
| low | Yes | ||
| high | Yes | ||
| index | No | Zero-based position; omit to append | |
| formId | Yes | ||
| lowLabel | No | ||
| required | No | ||
| highLabel | No | ||
| description | No | ||
| questionTitle | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Changes observed during successful MCP inspections.
v1.0.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, so the description bears the full behavioral burden, and a single clause discloses essentially nothing beyond the fact that something is added. No mention of default append behavior, index insertion, the required flag default, or the mutation's effect on the form. The verb 'add' implies a write but fails even a minimal mutation warning.
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?
One short sentence is superficially concise but this is under-specification, not conciseness. The sentence earns its place only by naming the resource; it economizes away every piece of value-add context an agent would need.
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 9-parameter form-mutation tool with no annotations and 21 siblings, one sentence is far from complete. The output schema covers return values and the index param has a schema description, but the agent still lacks where the question lands, when to prefer this over alternate question tools, and the meaning of the label and required parameters. Not a 1 only because the schema carries the hard constraints.
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 only 11% (just index), so the description needed to compensate for low/high, lowLabel/highLabel, questionTitle, and formId semantics — and it adds nothing. The phrase 'linear numeric scale' only weakly hints that low/high are endpoints. The schema's type and bound constraints (low 0-1, high 2-10) partially compensate and keep this just above the worst case.
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 and resource — 'Add a linear numeric scale' — which distinguishes it from add_text_question or add_choice_question by question type. However, it never says this is a form question/item, and with the conceptually adjacent add_rating_question sibling, the scale-vs-rating distinction is left unstated. The resource is named but its place in the form model is carried by the tool name, not the description.
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?
Provides zero when-to-use guidance. It does not contrast with add_rating_question or add_choice_question, states no conditions or exclusions, and never mentions form context or prerequisites. Among 21 siblings, the agent gets no routing aid at all.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.