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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower. The description adds useful context about what is inspected and over which windows (last 24 hours, last 30 days), and notes that a 'next_steps' field carries remediation guidance. It could still say whether the check is expensive or how absent events are reported, but it goes meaningfully beyond the annotations.

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?

The first sentence is a long comma-separated laundry list of returned fields that is hard to parse as a purpose statement; the actual purpose ('check the setup') is buried at the front of an overloaded sentence. Every item is relevant, but the structure would be clearer with the purpose stated first and the payload items separated out.

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?

There is no output schema, so the description must convey return content, and it does so in detail, including the remediation-oriented 'next_steps' field. Combined with the explicit usage trigger, an agent has enough to decide and call it, with only edge cases (no events at all, missing site) left implicit.

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?

The single 'site' parameter is fully documented in the schema (100% coverage), including the optional-with-site-key or single-site behavior. The description never mentions the parameter or how scoping works, so it adds nothing here. Baseline 3 applies when the schema does all the work.

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 ('Check the setup') and enumerates the diagnostic payload it returns: event arrival, first/last event, 24h counts by type, host names, and 30-day tracking-plan coverage. This is clearly distinguishable from siblings like get_overview or get_realtime by its install-verification and drift focus, though it never names or contrasts those siblings 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?

It gives an explicit triggering condition: 'Use it after you install the script or add events.' That tells the agent when this tool is the right call. It stops short of stating when not to use it or which sibling to pick for ongoing monitoring versus one-time install validation.

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