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

Annotations only declare readOnlyHint=true, and the description adds real context beyond that: the exact metric columns returned (first reply, first/total resolution, with and without business hours), the filterable dimensions, the sort capability, and the keyset-pagination caveat. It does not mention auth requirements, default date-window limits, or how to obtain the next cursor.

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?

Three sentences, front-loaded with what the report returns before filters, sorting, pagination, then the underlying endpoint. Dense but every clause carries information; the trailing 'Trengo: GET /reporting/details/ticket' is the least essential but still anchors the tool to a concrete API.

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 15-parameter, zero-required reporting tool with no output schema, the description covers the returned row shape, the filter surface, sorting, and the pagination strategy. Missing pieces are the default/required date-range behavior and cursor handling for subsequent pages, which keep it short of fully self-sufficient.

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%, so the baseline is 3. The description nonetheless adds meaning beyond the schema by pairing the timing metrics with their 'with and without business hours' variants, clarifying why both regular and _opening_hours sort options exist, and by summarizing the filter families and the start_after_ticket_id/page substitution rule.

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?

States a specific verb+resource ('Per-ticket reporting rows') and enumerates the returned fields (status, assignee, labels, first reply, resolution times), which clearly separates it from aggregate siblings like trengo_get_reporting_metrics and trengo_get_agent_performance. It never names those siblings, so differentiation is inferable rather than explicit.

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 one genuine usage rule given is pagination: 'For large accounts page with start_after_ticket_id instead of page,' which is useful and conditional. However, there is no guidance on when to prefer this report over trengo_get_agent_performance, trengo_get_reporting_metrics, or trengo_list_tickets, so alternative selection is left to inference.

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