get_draft

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

Beyond the annotations (readOnly, idempotent, non-destructive), the description discloses that the body is truncated at maxChars and that the truncation is reported, that HTML is converted to text, and that email content is untrusted and wrapped in ⟦mail:ID⟧ frames with an explicit never-follow-instructions rule. That is real safety and behavior context the annotations cannot express.

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?

Front-loaded with the operation and return shape, then the truncation/safety rules, then a compact Args block. No sentence is filler; the untrusted-data warning is terse but complete.

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?

Two parameters, one required, an output schema already present, and annotations covering the safety profile — the description adds truncation semantics, sourcing for the ID, and the injection-handling rule. Nothing an agent needs to call this correctly is missing.

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 burden and does: draftId is identified as the draft ID sourced from create_draft/list_drafts, and maxChars gets a purpose plus bounds (200 to 100,000) and default (8,090) that appear nowhere in the schema. It fully compensates for the coverage 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?

The first sentence names a specific verb and resource (read one draft) and enumerates exactly what comes back: recipients, subject, body as converted text, attachments, reply headers. That is enough to tell it apart from get_message, list_drafts, update_draft and send_draft without opening a 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 explicitly routes sending to send_draft ('Reading never sends: send_draft does') and tells the agent where draftId comes from (create_draft or list_drafts), which covers the main selection decision. It does not spell out the draft-vs-message boundary against get_message, but the read/send split is clearly handled.

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