create_draft

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

With no annotations, the description carries the full burden, and it does meaningful work: it discloses the 25 MB attachment cap, that local files are read from disk, that subject/to default from the original message when replying, and critically that nothing is sent. It omits error/permission behavior and what the returned draft object looks like, but the side-effect boundary is stated clearly.

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?

Three compact sentences, front-loaded with the core action, followed by threading behavior and then the no-send guarantee. Every clause conveys distinct operational information with no repetition of the schema.

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 7-parameter creation tool with no annotations and no output schema, the description covers the essentials an agent needs: what is created, attachment limits and local-file access, reply threading and defaulting rules, and that sending is out of scope. Remaining gaps (return value) are minor since the tool's contract is about producing a reviewable draft.

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 86%, so baseline is 3, but the description adds real semantics beyond the schema: reply_to_message_id implies subject defaults to Re: <original> and to defaults to the original Reply-To/sender (or original recipients), which the schema does not state. It also clarifies the attachment size constraint and that attachments are local file reads.

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 opens with a specific verb+resource ("Create a plain-text Gmail draft") and immediately distinguishes it from sibling draft tools by noting it never sends mail and that the draft is reviewed in Gmail. The scope qualifiers (plain-text, optional attachments, threading via reply_to_message_id) let an agent separate it from update_draft or read_draft without consulting the 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?

It gives clear usage context: use reply_to_message_id to make the draft a threaded reply, and the MCP never sends so the user must review in Gmail. It does not, however, explicitly say when to use create_draft vs update_draft (e.g., editing an existing draft) or name an alternative, leaving that to inference from sibling names.

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