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

Beyond the readOnlyHint=false annotation, the description adds meaningful behavior: omitted colors/fonts/radius default to the YouSpot kit, logos are not handled here, and the tool returns a brand_kit_id. These are real side-effect and return-value disclosures that help the agent predict consequences. Not exhaustive (e.g., no mention of overwriting or creation semantics), but solid.

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 tight sentences, each purposeful: the action and scope, required/default behavior, logo caveat, alternative routing, and return value. No fluff, and the most decision-critical information is front-loaded.

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?

Given 7 parameters, nested objects, and no output schema, the description covers the core essentials: creation scope, required field, defaults, logo handling, sibling alternative, and the returned brand_kit_id. It could additionally explain what happens to the active space or how dark_mode/documents defaults behave, but the schema already carries the documents purpose, so this is sufficient.

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 71%, and the description adds value by explaining the default behavior for omitted colors, fonts, and radius ('start from the YouSpot kit') and reinforcing that only name is required. This bridges a gap the schema alone does not fill. It doesn't clarify dark_mode or the fonts object structure further, but the enum values and other schema descriptions cover those reasonably.

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 brand kit by hand' in the user's active space. It distinguishes the scope clearly from the sibling extract_brand_kit, and also adds boundaries like logos being uploaded separately. The agent knows exactly what this tool does and what it does not do.

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 to the alternative: 'To import a brand from a website use extract_brand_kit instead.' The phrase 'by hand' and 'from what the user gave' establishes when this tool is appropriate versus the import path. No inference needed.

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