update_website_customization

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

Goes well beyond the annotations by disclosing the hidden partial-update wipe bug and the auto-fetch-and-resend workaround when header_font_family_id changes, plus the non-writable legacy fields that throw. These are exactly the kind of non-obvious mutation behaviors an agent cannot infer from destructiveHint/idempotentHint and are critical to calling the tool correctly.

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?

Front-loads the purpose and update semantics before the two long caveats, and every sentence carries actionable content. The final "Note" sentence is dense but justified given the severity of the wipe bug it warns about.

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-param, no-output-schema mutation with quirky API behavior, the description covers the high-value gotchas (wipe bug, restricted font IDs, non-writable fields). It reasonably assumes annotations carry the destructiveness signal and that color values are self-evident, so it is nearly complete.

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 63% (body_font_color, background_color, navigation_background_color have no descriptions), but the description compensates by stating the global 6-char-hex format and reinforcing the writability constraints and font-ID restriction. It adds genuine meaning, though it could have named the three undescribed color params explicitly.

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 ("Update website colors and fonts") that an agent can immediately map to customizing the wedding website's appearance. However, it never differentiates itself from the close sibling update_current_theme, leaving the boundary between theme selection and color/font customization to inference.

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?

Provides clear operational guidance ("Provide only what changes") and an explicit when-not rule for header_color/nav_font_color, directing the user to the web UI instead. It stops short of naming the alternative sibling (update_current_theme) for theme-level changes, so it falls short of a full when-to-use/when-not/alternatives treatment.

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