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

With no annotations, the description carries the full burden and does disclose real behavior: unsent fields are preserved (partial update), the settable surface is deliberately bounded, and a contract document governs the call. It does not address permissions, reversibility, or side effects such as breaking links when permalinkStructure changes, which is a meaningful gap for a mutation tool with zero annotation coverage.

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 field inventory, then the update/read rules in two short sentences, with zero filler. The field enumeration is somewhat dense but each gloss earns its place by disambiguating similar id-valued parameters.

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?

An output schema exists, so return values need not be explained, and the schema covers most parameters with descriptions. The description supplies the missing behavioral frame (partial update, bounded scope, contract doc) needed to call this safely against a large sibling set, falling short only on permissions and side-effect disclosure.

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 already 86%, so the schema baseline is 3; the description adds genuine meaning on top by framing the ids as page/attachment ids and tying siteIcon to an upload-media prerequisite. It reinforces the semantic role of each field rather than merely listing names, though a few fields (siteTitle, tagline) only get restated.

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 names a specific verb and resource (site-level settings) and enumerates exactly which settings are in scope, glossing each one (frontPage = home page id, notFoundPage = missing-address page). It explicitly separates itself from the read sibling get-site-settings and from other update-* tools by stating 'Nothing else is settable here by design.'

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?

It names the alternative for the inverse operation ('to read them, use get-site-settings'), states the partial-update rule ('Send only what changes'), and draws an explicit boundary ('Nothing else is settable here by design'). It also flags a prerequisite read of the site-settings-contract skill doc before the first call, though it gives no broader when-in-the-build guidance beyond 'the step every homepage build ends with.'

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