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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, so the safety profile is covered. The description adds behavioral context beyond that: it returns counts grouped by three specific statuses (not raw escalation data or a single total), and frames the operation as lightweight ('quick read'). This meaningfully clarifies what the agent should expect.

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 first states the operation and its dimensions; the second adds a brief purpose with no redundancy. The action verb is front-loaded, and every word earns its place.

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 zero-parameter aggregation tool, the description is complete. It states what is counted (escalations), the scope (current customer), the grouping (statuses), and the intended use. No output schema is present, but the expected return shape (counts per status) is obvious from the description, and annotations cover safety and idempotency.

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 tool has zero parameters, so the baseline is 4. The description correctly identifies the scope ('current customer's') without inventing parameters, and no additional parameter explanation is needed or possible.

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 uses a specific verb ('Count') and a specific resource ('current customer's escalations'), and further specifies the grouping dimension (status categories open, acknowledged, closed). This distinguishes it from sibling tools like list_escalations (which would list individual escalations) and get_escalation (single record). The added purpose note ('quick read on how much triage is waiting') reinforces what the tool is for, fully separating it from mere listing.

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 for when to use the tool: it is a summary/aggregation for a quick triage assessment, not a detailed list or a single-escalation view. However, it does not explicitly name alternative tools (e.g., list_escalations) or state when not to use it, stopping short of a full when/when-not comparison.

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