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

Adds substantial behavior the annotations cannot express: only passed fields change (partial update), design is a full replacement rather than a merge, edits go live on every page carrying the section at its next load, and the section type is immutable. The permission requirement (admin or owner) and the dashboard-only CSS caveat fill in the operational preconditions for a destructiveHint=true, openWorldHint=true mutation.

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-loaded and dense: purpose, update semantics, propagation, immutability, permissions, then a short Args block and return shape. The Args block re-states types and requiredness already present in the schema, which is mild duplication, but each sentence otherwise carries new information.

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, nested-object mutation with no output schema, the description covers what an agent needs: update vs replace semantics, live-effect timing, immutability, authorization, and the return shape ({ faq_section }). Multi-site handling is delegated to the thoroughly documented site_id in the schema, so nothing material is missing.

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?

With schema coverage at 88% the baseline is 3, and the description earns an increment by supplying semantics the schema leaves implicit: 'null clears it' for description, 'replaces the list' for display_urls, and 'design replaces the stored design'. It does not explain show_heading or the localized-object form of title/description, which the schema handles on its own.

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?

Opens with a specific verb+resource ('Change an FAQ section') and enumerates the mutable surface (title, description, display URLs, template, design), which cleanly separates it from helpcenter_create_faq_section, helpcenter_delete_faq_section and helpcenter_get_faq_section. It also names what is out of scope ('The type cannot change', 'Custom CSS is edited in the dashboard only'), so an agent can rule out siblings 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?

Gives clear operating context: admin/owner permission required, partial-update semantics, and explicit exclusions for type changes and CSS editing. It stops short of naming a concrete alternative (e.g., use helpcenter_update_template_settings or the dashboard for CSS) or stating when to prefer create_faq_section instead, so the routing guidance is contextual rather than explicit.

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