save_draft

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

Annotations already declare readOnlyHint=false, idempotentHint=true and destructiveHint=false; the description adds the key side-effect disclosure they do not cover — that no message is transmitted. It also conveys upsert semantics ("save or update"). It does not say whether an existing draft is overwritten or what permissions are needed, keeping it below 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?

Two short sentences, action first and the most decision-relevant constraint second. Every clause earns its place with no filler.

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?

Adequate for a two-parameter write tool with annotations covering the safety profile and no output schema to explain. The only real gap is what happens to a pre-existing draft, which matters for the upsert behavior it advertises.

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?

Two parameters with 50% schema coverage (conversationId is undocumented). The description's "draft reply on a conversation" loosely maps to both parameters but adds no format, length, or identifier details to compensate for the undocumented conversationId.

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 pair and resource: "Save or update a draft reply on a conversation." The closing "Does not send." draws a hard scope boundary against the send_message sibling, so an agent can pick the right tool without opening 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?

The "Does not send" clause implicitly signals when to choose this over send_message (preparing content rather than dispatching it), and "save or update" clarifies it handles both first draft and revision. It stops short of naming send_message or stating exclusions explicitly, so not a full 5.

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