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

Adds substantial context beyond the annotations: explicit partial-update semantics ('only the fields sent are changed'), the inheritance model (account defaults propagate to every website), and the downstream effect that the accent colour is interpolated into a stylesheet rendering on customers' sites. These are real behavioural traits an agent could not infer from destructiveHint/openWorldHint alone.

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: purpose, mutation semantics, scope behaviour, then the risk warning. Front-loaded and every clause earns its place, with the most consequential warning last but still compact.

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 9-parameter mutation with no output schema and only annotations for safety signalling, the description covers the two things an agent cannot guess: partial-update behaviour and scope inheritance. Remaining gaps (format expectations for URLs, whether an empty string clears a field, return shape) are minor given the self-descriptive parameter names.

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 11% — just 'project' is documented — so the description must carry the load. It explains the project parameter's scoping effect and adds meaningful context on accentColor (hex value, injection into a stylesheet), but says nothing about the other seven string fields (logoUrl, senderName, legalName, privacyUrl, termsUrl, mailingAddress, siteName) beyond what their names imply.

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 clear verb+resource ('Change brand settings') and immediately clarifies the two scopes it can operate on, which lets an agent separate it from read_brand. It stops short of naming the sibling or stating that it mutates account-level defaults vs. per-project overrides as a headline distinction.

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 gives concrete guidance on the decision that matters most — pass a project to set a website-specific override, omit it to change the shared account default — and spells out the blast radius of each choice. It does not mention any alternative tool (e.g. read_brand to inspect current values first) or prerequisites.

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