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

Annotations already declare idempotentHint, destructiveHint, and openWorldHint, but the description goes well beyond those booleans by spelling out the exact replay contract: same key + same args returns the saved result, while key reuse with different args or after a failed/uncertain send errors. That is precisely the nuance a boolean cannot convey. It still omits that a delivered email is irreversible and any account/permission requirements.

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 short sentences, zero filler, purpose front-loaded followed by the failure/replay conditions that matter most for a caller. Every sentence earns its place.

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 13-parameter send tool with no output schema, the description covers the highest-risk aspect (idempotent retry behavior) but leaves the body of the parameter space unexplained — particularly how draftId relates to to/subject/body, and attachment encoding. Adequate for the risky part, thin overall.

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% across 13 parameters, so the description must carry the semantic load, yet it only explains idempotencyKey (the required one) and says nothing about to/cc/bcc/from/subject/body variants/attachments/draftId/replyToMessageId/accountId/replyAll. The one explanation it does give is genuinely behavioral, but 12 params remain undocumented in both schema and description.

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 ('Send an email'), which is unambiguous on its own. However, it never distinguishes itself from the obvious sibling preview_send or explains the relationship to create_draft/update_draft, so the agent must infer the boundary.

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?

There is no when-to-use or when-not guidance, and no routing to alternatives such as preview_send (dry-run before sending) or create_draft. The description covers retry semantics but tells the agent nothing about when this tool is the right choice versus its siblings.

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