preview_send

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, and openWorldHint=true. The description adds the 'Does not send' safety reassurance and mentions it 'returns the required digest,' which adds value beyond annotations. But it does not detail what the digest contains or format implications. With strong annotations covering the safety profile, a 3 is appropriate.

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, front-loaded sentences with zero waste. The 'Does not send; returns the required digest' is efficient and clarifies both behavior and return. Could be slightly more informative about recipients format but is appropriately sized.

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?

The tool has 6 parameters including complex arrays for cc/bcc/attachments, an output schema exists, and annotations are solid. The description tells the agent this is a non-sending validation + digest return, which combined with annotations and output schema gives reasonable completeness. However, with 0% schema coverage on 6 parameters and no param guidance in the description, there's a gap around what the digest actually validates (address format? attachment presence? sendability?).

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 must compensate for 6 parameters. The description does NOT explain any parameter semantics, nor does it indicate which fields (email addresses vs filenames) the array parameters expect. Baseline should be 3 due to the coverage gap, and the description fails to add param-level 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?

The description clearly states the verb (validate and preview), the resource (an exact draft), and explicitly disambiguates from sending ('Does not send'). It distinguishes from sibling send_mail well, though it doesn't elaborate on what the 'required digest' is or how it differs from other preview tools.

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 description communicates the core context: this validates/previews rather than sends, implying it should be used before send_mail. However, it doesn't explicitly state when to use it versus alternatives like preview_batch_actions, nor when NOT to use it, and lacks guidance on prerequisites or ordering.

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