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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so safety needs no restatement. The description adds genuine context beyond them: the default-fallback behavior and the empty-result case when a brand has no design systems.

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: definition, forward usage with default, and empty case. The forward usage — the most decision-relevant fact — is placed early.

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?

An output schema exists so return values need no explanation, leaving the description responsible only for definition, downstream usage and the empty edge case — all present. Nothing an agent needs in order to call this 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 coverage is 100% and the brandId description already explains sourcing it from get_workspace or list_brands and omitting it for single-brand orgs. The tool description says nothing about brandId and only implies the id's downstream use, so the schema carries the load — baseline 3.

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 resource (the brand's design systems) and defines what one is ('a full look — logos, colours, fonts, design rules'), which no sibling tool does. The agent can distinguish it from list_brands, get_brand and list_entities immediately.

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?

Explicitly routes the result forward: pass an id as designSystemId to generate_design, generate_image or adapt_design, and states that omitting one yields the brand default. It stops just short of saying when not to call it (e.g. that it's unnecessary for a single-brand workflow already covered by get_brand).

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