bw_create_variable

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

With no annotations, the description carries the disclosure burden. It states observable behaviors: 'The variable is created active and consistent', and explains that setting ready_for_input false keeps a variable out of the variable screen. It also states scope limits on replacement path and unsupported variable types. Missing detail such as overwrite behavior or permissions is a minor gap.

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?

Four dense sentences with no filler. The core purpose and resource are front-loaded, then the caveats and exclusions are listed efficiently. Every sentence carries information necessary for invocation.

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 13-parameter tool with no output schema and no annotations, the descption provides enough context to understand supported types, representation, and key value (ready_for_input). The schema already covers all parameters, so the description does not need to restate them. It only omits details like whether an existing variable is overwritten, but that is a reasonable and not total gap.

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 complete at 100%, so the baseline is 3.0. The description adds value beyond the schema by clarifying the enum semantics, such as what 'UserEntry' means, the current-member-only restriction on ReplacementPath, and what 'ready_for_input' controls. This helps the agent choose valid parameter combinations.

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: 'Create a reusable BW Variable on a characteristic' and connects it to a concrete purpose ('use as a filter parameter in queries'). This distinguishes it from sibling create tools like bw_create_infoobject or bw_create_adso without needing to inspect the schema.

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 lists exactly which processing types are covered and explicitly excludes unsupported types: 'Text and formula variables are not supported' and 'replacement path is limited to the current-member variant'. While it does not name an alternative tool, there is enough context to decide whether this tool applies, and clear when-not-to-use signals are present.

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