get_unread_count

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

Describes the return format (dictionary mapping accounts to counts), which adds value beyond the empty input schema. But lacks explicit read-only hint or side effect disclosure. No annotations to fall back on.

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?

One concise sentence plus return format. However, the extraneous 'User Preferences' line does not belong and slightly reduces clarity.

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 tool with an output schema, the description adequately conveys purpose and return. Could be enhanced by mentioning any constraints (e.g., only primary account).

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?

No parameters exist; schema coverage is 100%. Per guidelines, baseline 4 applies. Description adds nothing about parameters because none are needed.

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?

Clearly states the tool gets the count of unread emails per account, with a specific verb and resource. However, it does not explicitly distinguish itself from sibling tools like get_recent_emails or get_inbox_overview.

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?

No guidance on when to use this tool versus alternatives (e.g., get_inbox_overview might also show counts). No when-not or contextual recommendations.

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