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

Annotations already signal read-only behavior, and the description adds useful non-obvious behavioral context: the tool is batch-oriented, returning per-monitor breakdowns, and looping is expensive and rate-limit-prone. This goes beyond the annotation's safety profile, though it does not describe response shape in detail.

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 focused sentences with no fluff: the first states what the tool computes, and the second delivers the only critical invocation nuance. The most important usage warning is front-loaded and direct.

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 simple read-only aggregation tool, the description plus fully documented schema parameters cover what an agent needs: metric, unit, date-window defaults, batching behavior, and rate-limit caution. No output schema exists, but 'MTTA per monitor, in seconds' provides adequate expectations for the return value.

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 description coverage is 100%, so the schema already documents all three parameters thoroughly, including defaults and batching semantics. The description repeats the batching point but adds no new parameter-level meaning beyond what the schema already provides, matching the baseline of 3.

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 clearly states a specific metric (MTTA), the resource (monitors), and the unit (seconds), so an agent immediately knows what the tool computes. It does not explicitly distinguish itself from the near-named sibling get_monitor_mttr, but the phrase 'mean time to acknowledge' makes the purpose specific enough to avoid serious confusion.

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 gives clear context: it applies to a date window and is already per-monitor, and it instructs the agent to pass all monitors at once rather than loop. It does not explicitly mention when to choose this tool over get_monitor_mttr or other metrics, so it stops short of full when/when-not guidance.

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