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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is clear. The description adds valuable behavioral detail beyond that: it discloses that the preview is capped at 100 and reports truncation, and it explicitly guarantees that customer identifiers, staff ids, message text, and organization ids are never returned. These privacy and data-scoping guarantees are important for agent decision-making and are not in 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?

Two sentences, each earning its place. The first sentence defines the core action and grouping; the second addresses the preview cap and privacy guarantees. Information is front-loaded and there is no fluff.

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?

Given there are no parameters, an output schema exists (though not shown in the prompt), and annotations cover safety, the description covers all crucial aspects: what it counts, the grouping dimension, the cap on the preview, the truncation reporting, and the explicit data that will never be returned. An agent has everything needed to call this tool correctly and interpret the results.

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 schema is trivially complete. The description doesn't need to explain any parameters. The absence of parameters is clear from the schema, and the description focuses on behavior rather than parameter details. Since there is nothing to clarify, a perfect score is appropriate.

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 ('count'), a clear resource ('unresolved conversations'), and the aggregation dimension ('grouped by website'). It clearly distinguishes this from siblings like list_conversations (which would return individual conversations) and get_conversation (a single conversation), by emphasizing the counting and grouping aspect.

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 when to use this tool: when you need aggregate counts of unresolved conversations grouped by website, rather than the conversation list itself. It doesn't explicitly name alternative tools, but the phrasing 'Count every unresolved conversation... grouped by website' makes the use case self-evident. It also gives specifics about the capped preview and truncation reporting, which helps an agent decide if this tool meets its needs.

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