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

Annotations already declare destructiveHint=true, readOnlyHint=false and idempotentHint=true, so the safety profile is covered structurally; the description usefully adds that writes land 'straight into the draft' and that 'the change is immediate'. It does not restate what is overwritten versus merged (the palette's replace semantics live only in the schema), so a small gap remains.

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?

Three sentences, front-loaded with the write action, then alternatives, then the two special cases. It is dense and telegraphic (the 'ROOT `company` vars' fragment assumes prior context) but every sentence carries routing or workflow information, so there is little 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 a 14-parameter, nested-object, no-output-schema mutation tool, it covers the essentials: what is written, that it affects the draft immediately, which siblings to use instead, and where the controlled vocabularies live. What it omits — merge-vs-replace behavior for the palette and any validation/permission requirements — is largely handled in the schema, leaving only minor gaps.

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 description coverage is 100%, so the baseline is 3, but the description adds real navigation value by telling the agent where the palette-name and styleGuide-key vocabularies come from (get_style_reference topic "theme") and by flagging that fonts hints are only used when styleGuide omits families. With 14 params and nested objects, that pointer meaningfully reduces lookup friction.

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 ('Write') and resource ('the site theme') and then enumerates exactly what is written: preset, palette, darkPalette, styleGuide tokens and fonts, and JSON-LD. It also names the sibling tools that look similar but do not write, so the agent can separate this tool from suggest_palettes/suggest_font_pairings without opening a schema.

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 the agent: suggest_palettes / suggest_font_pairings are named as the non-writing alternatives that 'only show options', ROOT `company` vars are redirected to patch_site_node, and the workflow/key-list reference get_style_reference({ topic: "theme" }) is given. Both an alternative and a companion call condition are spelled out.

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