save_draft_email

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

Annotations already declare readOnlyHint=false, idempotentHint=false and destructiveHint=false, so the safety profile is covered. The description adds real context beyond that: the message is appended to the special-use Drafts folder with the \Draft flag, the user reviews/edits/sends from their own client, and 'Each call creates a new draft' independently confirms the non-idempotent behavior. It does not describe the return value or failure modes (e.g., invalid account, missing file), so not a full 5.

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?

Purpose is front-loaded, followed by behavior and then the argument list; every sentence earns its place and the size is proportionate to 10 parameters. The Args block is somewhat list-like, but each entry carries non-obvious meaning rather than restating the parameter name.

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 10-param mutation tool with no output schema and zero schema description coverage, the description covers the write path, folder placement, threading fields and the send-vs-draft decision well. Missing pieces are minor: nothing about what the call returns (e.g., a draft identifier) or which folders/accounts are valid beyond list_accounts.

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%, so the description carries the entire burden, and it documents all 10 params with real semantics: account comes 'from list_accounts', html is an 'alternative to the plain-text body', attachments are 'Local file paths', and in_reply_to/references are explained in terms of threading. It stops short of format specifics (e.g., address string format, accepted date/ID syntax), so there is a small residual gap.

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?

States a specific verb+resource ('Compose an email and save it to the account's Drafts folder without sending it') and immediately disambiguates from the closest sibling by name ('Use this instead of send_email'). An agent can distinguish it from send_email/reply_email/forward_email without opening any schema.

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?

Gives an explicit selection rule: use this instead of send_email 'whenever the user wants to check a message first.' The alternative and the condition that selects it are both stated, leaving nothing to inference for the primary send-vs-draft decision.

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