update_website_customization

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

With only destructiveHint: false in annotations, the description carries the behavioral burden and succeeds: it discloses the auto-fetch/re-send workaround for the Zola partial-update wipe bug, the throwing behavior of two non-writable parameters, and the restricted body_font_family_id range with its generic-error failure mode. No contradiction with the annotation.

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 sentences, each earning its place: purpose, update semantics, color format, bug workaround, field restrictions. The Zola bug sentence is long and dense, but it conveys critical behavior that would otherwise surface only as a runtime surprise. Slightly heavy on a single compound sentence, but no waste.

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 an 8-parameter, all-optional write tool with no output schema, the description covers format constraints, value restrictions, bug behavior, and field-level alternatives. Minor gaps: no statement of what happens when zero parameters are passed, no return-value description, and header_font_family_id validation only appears in the schema, not the description. These are small relative to the breadth disclosed.

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?

The description adds the 6-char hex-without-# format rule and the partial-update semantics that only provided fields are touched — details the schema lacks for the color parameters. It reinforces the schema's body_font_family_id restriction and the non-writable header_color/nav_font_color. At 63% schema coverage, the description meaningfully compensates for undocumented parameters.

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 opens with a specific verb+resource pair — 'Update website colors and fonts' — making the tool's scope immediately clear. This distinguishes it from read siblings like get_website_customizations and theme-level tools like update_current_theme, though it doesn't explicitly name any sibling. The purpose is unambiguous and precise about what domain the update touches.

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 clear usage context: 'Provide only what changes' establishes partial-update semantics, and it explicitly directs the agent to the Zola web UI for header_color and nav_font_color, which throw if passed here. It does not explicitly reference sibling MCP tools as alternatives, but the field-level when/where guidance is strong and actionable.

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