count_unread

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It only states the action and gives no information about return format, side effects, permission requirements, or whether the count is scoped to a specific account or folder. There is no contradiction with annotations because none exist.

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?

The description is a single sentence with no redundant words. It front-loads the action ('Count') and the resource ('unread Unibox messages'), making it maximally concise and directly scannable.

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 is no output schema or annotations, the description is the only source of context. It clarifies the core purpose but omits the return format and the meaning/scope of 'Unibox'. For a parameterless read-only count this is mostly adequate, but an agent could mis-handle the response or misunderstand the coverage of the count.

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 already complete (100% coverage by definition). The description does not need to add parameter-specific meaning, and the baseline for zero-parameter tools is 4.

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' and resource 'unread Unibox messages', and it is the only count-related tool among siblings so it is distinguishable from list_emails and mark_thread_read. However, the term 'Unibox' is not defined and the scope (global vs. per-account) is left implicit.

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?

There is no guidance on when to use this tool versus alternatives such as list_emails or mark_thread_read. No exclusions, prerequisites, or context clues are provided beyond the obvious 'count unread' use case implied by the name.

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