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

Annotations already declare destructiveHint=true and readOnlyHint=false, but the description adds materially more: that `text` OVERWRITES copy shared by the layout elsewhere in the project, that both the sitemap node and variant map are mutated together, and that blog pages enforce a hard section whitelist with refusal behavior. These are non-obvious, high-consequence details an agent could not infer from the annotations.

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?

Dense but nearly every sentence adds non-redundant information (overwrite semantics, dual-document write, slot-filling alternative, blog constraints). The structure is the weak point: it opens with a caveat about `text` rather than the core action, so the purpose statement lands second, and the all-caps blog block is louder than its relative importance.

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 destructive, 7-parameter, nested-object mutation tool with no output schema, the description covers the important behavioral risks: shared-layout copy overwrite, dual-document consistency, and page-type restrictions. It does not say what the call returns or whether the new section's identifier/index is reported back, which an agent planning follow-up edits would want.

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 43% across 7 parameters, so the description carries a real compensation burden. It adds meaningful semantics for `text` (slot tokens belong to the layout, overwrite scope) and implies `index` via 'at a position', but says nothing about `images`, `projectId`, or `pageName`, and does not clarify the required `variant` layout-id resolution beyond what the schema already states. Partial compensation only.

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: 'Add a section to a page at a position.' It also distinguishes itself from the failure mode of editing only one document, which implicitly separates it from sibling tools like replace_section or set_section_style. However, the actual purpose statement is buried in the second sentence behind a caveat about copy overwriting, so the agent has to read past a warning to learn what the tool does.

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 to sibling tools ('call uichemy_template_slots and pass `text`'), names the data sources for the required fields (uichemy_list_section_kinds, uichemy_list_templates), and provides a concrete when-not clause: BLOG PAGES ARE CONSTRAINED, with the exact allowed section set per blog page type and the note that disallowed sections are 'refused, not added.' That is about as complete as usage guidance gets.

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