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

Annotations already declare destructiveHint=true, idempotentHint=true and readOnlyHint=false, so the mutation/idempotency profile is covered. The description adds one genuinely new behavioral fact — the merge semantics of omitted fields — but does not warn that sending null wipes saved config (left to the schema) or that removing a selector is destructive to the saved check set.

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 sentences, zero filler, with the scope of the change front-loaded and the merge rule placed last where it governs the whole operation. Nothing is restated from the title.

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 4-parameter tool with deep nested objects, 100% schema coverage and full annotations, the description is sufficient: it identifies all three config groups, the merge contract, and the key concept of each. Remaining gaps (return value, monitor-type applicability) are minor given the stated schema richness and the absence of an output schema.

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 100% and the property descriptions already spell out nested structure and null-to-clear behavior. The description nevertheless adds semantic gloss the schema lacks — mustContain/mustNotContain described as words the page must or must not contain, and selectors as checks on parts of the page — which helps an agent pick the right config block.

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?

Names a specific verb (change) and precisely enumerates the three check families it governs — keyword checks, per-selector content checks, and freshness/updated-recently checks. That vocabulary clearly separates it from the many sibling vs_monitors_update_* tools (expectations, visual, performance), though no sibling is named explicitly.

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 closing clause "Only the fields sent change" gives essential partial-update guidance, implying when this tool is safe to call incrementally. However, it never states conditions for choosing it over e.g. vs_monitors_update_expectations or vs_monitors_bulk_update, nor any prerequisites such as the monitor type the checks apply to.

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