create_draft

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

With no annotations, the description carries the full burden. It does disclose two non-obvious behaviors: nothing is sent, and tokens like [[EMAIL_1]] are substituted with real values. It omits permissions, which folder is used if ambiguous, and what (draft id?) is returned for chaining into update_draft.

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?

Two short sentences with the creation statement and the not-sent warning front-loaded, then the token rule. No filler; the stray escaped newline is the only blemish.

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 four-parameter mutation tool with no annotations and no output schema, the description should say what is returned (e.g. a draft identifier needed by update_draft or delete_draft) and clarify recipient formatting. Those gaps make it incomplete for correct chaining.

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% for four parameters, so the description must compensate but largely doesn't: it never explains to vs cc, subject, or body, nor whether recipients are comma strings or arrays. Only the token-substitution rule for parameter values adds real meaning.

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 and resource ('Skapa ett nytt utkast') plus the target location ('Utkast-mappen'), and adds the key constraint that it is not sent. It doesn't name create_reply_draft or update_draft, so the boundary with the closest siblings is left to inference.

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 'Skickas INTE' clause implies this is for composing without sending, which is useful context, but it never says when to prefer create_reply_draft (for replies) or update_draft (for existing drafts). Usage is implied rather than stated.

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