Create a brand (reusable style token set)

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

Given the annotation openWorldHint=false, the description goes beyond annotations by explaining that brands are style-only and cannot inject data, which is a key behavioral trait. It also reveals resolution order (ENGINE_DEFAULTS <- brand <- chart config) and that unknown keys are rejected, which is crucial for safe invocation. However, it doesn't state any side effects (e.g., if making a brand default overrides existing defaults) or specific error responses beyond key validation.

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 concise but information-dense, with the most critical information (the tool's purpose and usage) front-loaded. Each sentence contributes unique value: the first explains the tool's core function and usage, the second clarifies its non-capabilities, and the third is embedded in parameter semantics but is still efficient. No fluff or redundancy.

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 tokens object and no output schema, the description provides enough guidance for an agent to invoke it correctly: explains the structure of tokens, the resolution order, the need to fetch the schema for exact keys, and the restriction on text. However, it doesn't detail the return value or any side effects of setting isDefault, which could be a gap, but the annotation openWorldHint=false and the clear instructions mitigate that.

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 75%, meaning three of four parameters have descriptions. The description adds significant value for the 'tokens' parameter by explaining the expected structure, the resolution order, and caution about unknown keys. The 'slug' parameter's pattern is in the schema, but the description doesn't add much beyond the schema's example. However, the high coverage means the schema does most of the work, and the description supplements the most complex parameter effectively.

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 clearly states the tool's purpose: creating a brand that styles assets, with a specific verb ('Create') and resource ('brand'). It distinguishes this from siblings like update_brand by focusing on the creation aspect and how brands apply. It also clarifies what a brand is not (cannot inject data), adding precision.

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 strong context on when to use this tool (to create a brand for styling assets) and implies when not to (since brands are only for styling, not data). It doesn't explicitly name alternatives like update_brand, but the context is clear enough for an agent to infer the distinction. It also explains how to apply the brand (via brand: "<slug>"), which guides usage.

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