Save a template

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

The description goes well beyond the sparse annotations. It clarifies the key side effect—no survey is started—and explains the reuse behavior: each launch via launch_template creates a fresh survey, keeping weekly poll answers separate. It also discloses lifecycle limitations upfront: templates cannot be edited or deleted through this API. This meaningfully informs an agent about what to expect after invocation.

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?

Three sentences, each earning its place: the first states the core action and what it avoids, the second explains the practical reuse pattern with a concrete example, and the third sets boundaries for template management. The most important information is front-loaded, and there is no filler.

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 tool with a complex nested questions schema and no output schema, the description covers the essential operational context: what saving means, that it does not start a survey, the relationship to launch_template, and where editing/deleting happens. It does not describe the return value, but given the absence of an output schema and the richness of the input schema, the description is still sufficiently complete for correct selection and invocation.

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?

The description itself adds no parameter-level detail, but the input schema is fully covered (100%) with rich descriptions, including the meaning of `name`, the structure of `questions`, and the semantics of conditional `requirement` logic. Baseline 3 is appropriate because the schema already carries the heavy lifting.

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 opens with a specific verb and resource: 'Save a set of questions for reuse' and immediately distinguishes itself from creating a survey by adding 'without starting a survey.' It also names the related launch_template tool, so there is no ambiguity about what create_template does.

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 explicitly tells the agent when not to use this tool ('without starting a survey'), points to the correct alternative for launching later ('Launching it later with launch_template'), and gives an exclusion for editing/deleting templates ('done on rifts.to, not here'). This is proactive routing guidance that removes guesswork.

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