get_mailbox_unread_counts

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

No annotations are provided, so the description carries the full burden. It discloses both return formats (nested dict vs flat dict) and explains all parameters. It does not mention side effects, but since it's a read operation, this is sufficient.

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 concise, well-structured with Args and Returns sections, and contains no redundant information. Every sentence serves a purpose.

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 that an output schema exists, the description already covers return values and parameter behavior. For a read tool with three optional parameters, the description is complete and covers all use cases.

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 0%, but the description fully explains each parameter's purpose: account filter, include_zero handling, and summary_only mode. This adds significant meaning beyond the schema.

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 clearly states the tool gets unread counts per mailbox for one account or all accounts. It uses a specific verb ('Get') and resource ('mailbox unread counts'), and distinguishes itself from siblings by focusing on unread counts.

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 provides guidance on when to use summary_only=True versus False, noting it replaces the former get_unread_count tool. It could be more explicit about when to use alternative sibling tools, but it clearly explains the parameter options.

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