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

Annotations only declare the safety profile (readOnly=false, destructive=false, openWorld=false), and the description goes beyond that by explaining the downstream effects: the Design canvas renders one card per page in this order while the Site map keeps category containers fixed and reorders only within them. That is genuinely useful behavioral context. It stops short of stating permissions, error behavior, or what happens to pages omitted from the list.

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 with the imperative, then constraints, then effects. Four sentences with no filler, though the Design canvas / Site map explanation is slightly longer than strictly needed to invoke the tool correctly.

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 two-parameter mutation with no output schema, the description covers the critical semantics: input shape, the home-page invariant, and how the order manifests in the UI. It omits edge-case behavior (invalid/duplicate/missing page names, effect on published sites), which is the remaining gap.

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 50% (projectId is undocumented), so the description must carry weight for 'order' — and it does, specifying completeness ('every page name exactly once'), ordering semantics, and the home-page-first invariant that the schema's one-line description only gestures at. It adds real meaning beyond the schema, though projectId remains entirely unaddressed.

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 ('Put the pages in a new order') and immediately scopes it as a whole-project page ordering, which cleanly separates it from the sibling uichemy_reorder_sections and uichemy_duplicate_page. An agent knows exactly what operation this is without opening the 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?

The description gives strong invocation rules ('pass every page name exactly once', 'home page stays first') but never states when to reach for this tool versus alternatives such as uichemy_reorder_sections or uichemy_set_page_category, nor any preconditions (e.g. project must exist, pages must be known). Usage is implied rather than routed.

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