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

Annotations already declare destructiveHint=true and readOnlyHint=false, but the description adds genuinely new behavior: the result is non-persistent unless apply is true, PDF extraction may suggest tone styles without touching the strategy brief, and AI usage must be confirmed. That detail materially changes how an agent should sequence the call.

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?

Five short sentences, front-loaded with the input constraint and the preview-vs-apply distinction. No sentence is filler; each adds a constraint or an effect.

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 destructive, non-idempotent, open-world mutation with no output schema and thin schema descriptions, the description covers inputs, authorization, persistence semantics, and a notable side effect. Missing only the role of brandId and any hint of how this pairs with get_brand_kit/update_brand_kit.

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 only 20%, so the description carries most of the burden and does so for siteUrl/pdfPath (mutually exclusive, one required), apply (persist vs. preview), and confirm (AI authorization). The brandId parameter is never explained in either place, leaving one real gap.

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 (Extract) and resource (visual identity / brand kit) and constrains the input to 'exactly one of siteUrl or pdfPath'. It also separates itself from the analyze_* siblings with 'Does not analyze the business', so an agent can tell it apart without opening other schemas.

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?

Gives clear preconditions (exactly one source, confirmed AI usage) and explains the default vs. opt-in flow ('returns a suggested kit without applying it; apply true saves it'). It stops short of naming the sibling to use instead when the agent wants to read or modify an existing kit (get_brand_kit / update_brand_kit).

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