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

Annotations already cover the safety profile (read-only, idempotent, non-destructive), and the description adds real behavioral context beyond that: 'One predicate determines both the total and page' and 'AI drafts are not counted as sent replies' are non-obvious counting semantics. Pagination behavior via limit/offset is also noted.

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?

Four short sentences, each carrying a distinct point (scope, predicate behavior, counting rule, pagination), with the queue scope front-loaded. Efficient with no filler, though slightly clipped in tone.

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?

A read-only list tool with no output schema, so the description ought to say more about the returned shape or the total field it mentions. It covers pagination and counting semantics adequately but leaves the return payload undocumented for a tool where the schema is silent.

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 mode, limit, and offset, and the baseline is 3. The description mostly restates the limit/offset mechanics already in the schema rather than adding format or edge-case meaning.

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 ('List') and resource ('reply-needed conversations or due follow-ups'), and the two modes map cleanly to the 'mode' enum. It is clear what the tool returns, though it never differentiates itself from siblings like get_conversation_context or get_daily_priorities.

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 phrasing 'in the selected product' implies a product-scoped context but gives no explicit when-to-use signal or named alternative. An agent must infer that this is the queue view for triaging replies versus other conversation tools.

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