get_unread_emails

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

With no annotations, the description carries the full burden of disclosure. It states 'fetches' which suggests a read-only operation, but does not clarify whether the email is marked as read, what 'recent' means (time window or count), or what 'details' are returned. This leaves ambiguity about side effects and output structure.

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, concise sentence that says exactly what the tool does without unnecessary repetition or filler. It is well-structured and front-loaded with the verb.

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 simple, parameterless tool, the description communicates the core functionality adequately. However, it lacks specifics on output format (what fields constitute 'details') and the meaning of 'recent', which would improve completeness given there is no output schema.

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 input schema is empty, so there are no parameters to describe. The description's phrase 'recent unread email details' effectively implies the scope of the operation, earning a baseline 4 for tools with zero parameters.

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 uses a specific verb ('fetches') and identifies the exact resource ('recent unread email details from Apple Mail'), making the tool's function immediately clear. It is clearly distinct from sibling tools like send_email, which sends rather than reads messages.

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 context of retrieving unread emails is stated, but there is no explicit guidance on when to use this tool versus alternatives or any exclusions. The presence of sibling tools like send_email implies this is the read counterpart, but that is not explicitly stated.

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