email_get_categories

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

With no annotations at all, the description carries full burden for behavioral disclosure. It does not state whether the operation is read-only/safe, whether the account must be pre-authenticated, what happens for non-Outlook accounts, error behavior, or what the returned category structure looks like. For an account-scoped read operation, key context is missing.

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, efficient sentence that conveys purpose and platform scope without waste. It is appropriately front-loaded with the core action. Minor room for improvement exists in adding behavioral context, but the brevity is structurally sound.

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?

With no annotations, no output schema, and 0% parameter coverage, the description alone must make this tool self-sufficient. It does not explain the return value format, category semantics, or account prerequisites, and it leaves the distinction from sibling email_get_labels unexplained. For an account-scoped operation with zero supporting metadata, this is materially incomplete.

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 0%, so the description must compensate for the single parameter. The tool name and description make it clear 'accountId' refers to the email account being queried. While the description doesn't explicitly define accountId, the context is unambiguous given only one parameter exists whose purpose is inferable from name and tool purpose.

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+resource ('List all categories for an email account') and clearly distinguishes this tool from siblings focused on labels, folders, and threads. The 'Outlook only' qualifier adds scoping value. It slightly differs from sibling email_get_labels, which is a meaningful distinction retained by the account-scope phrasing.

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 'Outlook only' parenthetical provides a platform constraint that helps the agent decide when this tool applies. However, there is no explicit guidance on when to prefer this over email_get_labels, which is a close sibling, nor any statement of prerequisites (e.g., account must exist, must be Outlook) or when not to use it.

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