email_delete

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 does state the key behavior (trash vs permanent delete), but omits important details like whether deletion is reversible, what happens to attachments, permission requirements, and the sourceFolder requirement for non-INBOX IMAP/iCloud emails. The 'permanently deletes' implication should also explain the irreversibility.

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, compact sentence that efficiently conveys the core behavior and default. It is appropriately front-loaded with no waste, though it could trade some brevity for critical detail like the permanence irreversibility.

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 destructive mutation tool with no annotations and no output schema, the description is thin. It has 4 parameters but only 25% schema coverage, a destructive default with a permanent escalation option, and no explanation of side effects, permissions, or the sourceFolder edge case. A tool of this risk profile needs more thorough behavioral disclosure than a single clause provides.

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 only 25% (only sourceFolder has a description). The tool description notes the 'permanent' parameter's effect and the default trash behavior, adding some meaning beyond the schema. However, it does not explain the sourceFolder requirement despite this being a subtle, error-prone parameter, and does not clarify the accountId/emailId combination beyond schema titles.

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+resource (delete email) and clearly states the default behavior (moves to trash) versus permanent deletion. This distinguishes it from sibling tools like email_get, email_move, and email_batch_delete, though it doesn't explicitly contrast with email_batch_delete.

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 does not state when to use this tool versus alternatives like email_batch_delete. It also omits important context such as whether the permanent flag requires confirmation, and does not mention prerequisites like the sourceFolder nuance for IMAP/iCloud that appears in the schema.

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