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

Annotations already declare the safety profile (readOnly=false, idempotent=true, destructive=false), so the bar is lower. The description adds real value beyond them: it discloses that restoreAll reverses *every* dismissed recommendation, which is a scope-changing behavior an agent must know before calling. It does not clarify whether a dismissed recommendation is permanently deleted or merely hidden.

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?

One sentence, front-loaded with the primary action and with the alternative held to a parenthetical plus a trailing clause. No filler. Slightly dense because it packs two operations into a single sentence, but nothing is wasted.

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?

Covers the two main modes and the restoreAll scope, and with no output schema there is no return format to explain. However, for a 3-parameter mutation tool it leaves a real gap: the interaction between the optional key and restoreAll (what a bare siteId call does) is unaddressed, and no reversibility caveat beyond restoreAll is given.

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% — key and siteId are documented, but the restoreAll boolean has no schema description. The description compensates by defining restoreAll's effect ('bring every dismissed recommendation back'), which is exactly the missing semantic. It adds no extra detail on key/siteId pairing, but the schema handles those.

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 ('Stop recommending a monitor for a site') and discloses a second mode via restoreAll. It also names where recommendations surface (list_checks), which helps an agent place the tool, though it does not contrast itself against the other dismiss/ignore siblings (ignore_finding, ignore_structure_change).

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 implies two usage modes — dismiss one monitor by key, or bulk-restore with restoreAll — but never states when to pick one over the other, nor what happens if key is omitted without restoreAll (only siteId is required by the schema). Usage is inferable but not explicitly guided.

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