update_option

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

Annotations already declare idempotentHint true and destructiveHint false, so the mutation/read-only profile is covered. The description adds that the updated option is 'refetched via the parent question' and that the return is a JSON of the updated option, giving the agent a clear model of the side effect and result. It also warns about not using `order`, which is a behavioral constraint not in annotations.

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 description is extremely concise: a single purpose line, a structured args block, and a returns line. Every sentence adds value, and the exclusion of `order` is front-loaded. No unnecessary fluff; the structure is scannable and efficient.

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?

Given the tool requires three IDs and a nested object, the description covers all required parameters and their meanings. The return behavior is specified, and since there is an output schema, it needn't detail the exact JSON structure. The warning about `order` is a critical edge case that is addressed. Nothing the agent needs to call 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 descriptions are entirely absent, so the description must fully compensate. It explains each parameter: form_id, question_id, option_id as numeric IDs, and key_value_pairs as 'Object with fields to change. Common keys: text (str).' It also adds the critical warning about `order` and alternative tool. This is a complete semantic mapping.

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 begins with a clear verb+resource statement: 'Update an option's properties.' It specifies the action on a distinct resource (option), differentiating it from sibling update tools like update_question or update_form. The explicit exclusion of 'order' and referral to reorder_options further rules out overlap.

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 provides a clear when-not-to-use rule: 'Do NOT pass `order` — use reorder_options instead.' This directly guides the agent to the correct sibling for ordering operations. It implies this tool is for updating other properties (e.g., text), but does not enumerate specific scenarios beyond that.

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