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

Annotations already declare the safety profile (non-destructive, idempotent, closed-world), so the bar is lower; the description still adds the meaningful behavioral fact that this is a partial merge rather than a full replace, and that other settings are untouched. That is exactly the kind of context annotations cannot convey.

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?

Two tightly written sentences: the changeable surface is front-loaded, then the partial-update rule, then the exclusions. No filler sentences and every clause carries load.

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 no-required-param settings mutation with annotations covering safety and no output schema, the description supplies partial-update behavior and scope boundaries. It omits any mention of permission/auth requirements, which is the only notable 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 67%, and the description fills the gap by spelling out the frequency enumeration (instant and/or daily/weekly digest), what digest timing controls, and the minSeverity/everyRun meaning. It leaves timezone and digestWeekday to the schema, which already documents them adequately.

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 (change) plus the exact settings surface — alert frequency, digest timing, minimum severity, and everyRun emailing — and explicitly names the adjacent settings it does NOT touch (who gets alerts, muting, disabling email). An agent can separate this from update_site_settings or get_alert_settings 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 usage context via partial-update semantics ('Only the fields you pass change') and routes excluded concerns to the dashboard, which acts as an alternative surface. It does not name a sibling tool for reading current settings, so it falls just short of explicit when/when-not routing.

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