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

Annotations already flag destructiveHint=true and idempotentHint=true; the description adds real value beyond them by spelling out whole-list replacement, that an empty list empties a menu, that omitted menus are preserved, the 20-link cap, immediate reader visibility, and the special behaviour of member-door links. The closing sentence 'An admin's.' is a truncated fragment, leaving the permission/authorization requirement ambiguous — a meaningful gap for a destructive 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?

It is dense and information-rich, but written in a telegraphic register with sentence fragments ('On one site of the account, named in site.', 'An admin's.') and an unclear terminal clause. The key replacement semantics are near the front, but the clipped phrasing adds parsing cost that a slightly more conventional structure would avoid.

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, no-output-schema mutation over three parameters, the description covers what is replaced, what is preserved, ordering, size limits, and visibility of the change. The only shortfall is the incomplete authorization note and no guidance on the response or confirmation of the resulting state.

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 a 3 would be the floor, but the description goes further: it disambiguates the two array parameters by their rendered location (masthead vs footer), defines them as whole ordered lists rather than patches, and adds constraints (20 links max) plus a note on how member-door URLs behave. That is meaning an agent could not derive from the schema alone.

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?

The description states a specific verb and resource: it replaces the site's menus via Settings › Design › Navigation, and explicitly maps 'navigation' to the masthead (Primary) and 'secondary_navigation' to the footer (Secondary). It also names get_navigation as the read-side counterpart, so an agent can distinguish it from sibling tools 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?

'Replaces one of the site's menus, or both' plus 'a menu left out stays as it is' tells the agent exactly when a call is partial vs full, and 'get_navigation lists the site's own links' points at the read alternative for inspecting current menus before writing. There is no explicit when-not-to-use statement (e.g. for theme-defined menus), so it falls short of a full 5.

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