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

Annotations already provide destructiveHint=true, readOnlyHint=false, and idempotentHint=false, so the description's 'destructive' tag is largely redundant. It does add that the operation affects exactly one draft and that the ID must come from list/create, which helps prevent misuse. It does not mention permanence/irreversibility, but the destructive annotation already signals that risk.

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 short sentence that front-loads the core action, then adds the necessary input source and a destructive warning. There is no filler or repetition beyond the intentional emphasis on destructiveness.

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 two-parameter destructive tool, the schema and annotations cover parameter semantics and safety, while the description clarifies scope and input provenance. It lacks an explicit note about response/confirmation behavior and does not distinguish from email_trash, but the essentials for correct invocation are present.

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 100%, and the schema already documents draft_id as the exact ID from email_list_drafts/email_create_draft with a warning not to use subject or email_id. The account_id schema also provides detailed guidance. The tool description only restates ID provenance and adds no new parameter meaning, so the baseline 3 applies.

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 starts with a specific verb and object: 'Discard one exact draft.' This clearly identifies the tool as a single-draft deletion operation. It does not explicitly name sibling tools like email_trash or email_delete_folder, but the scope ('exact draft') plus the title make the purpose unambiguous.

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 gives a useful usage cue: the draft_id must come from email_list_drafts or email_create_draft, implying the tool is for drafts that already exist. However, it does not explicitly mention when to prefer this over alternatives such as email_trash, nor does it state exclusions. The destructive warning is a caution, not a usage routing.

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