email_send

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

With no annotations provided, the description carries full behavioral burden once-per-send and idempotency guarantee are disclosed. It states two safety inputs are 'required' but doesn't document side effects beyond sending, error cases, or what happens on idempotent retries. The 'exactly one email' and 'reuse it only for the identical send request' hint at retry semantics without full detail.

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?

The description is compact (three sentences) and front-loaded with the most critical safety constraint. Every sentence contributes value: requirement, attachment selection options, and confirmation semantics. No filler or redundant restatement 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?

The tool has 9 params with 6 required and no output schema, so the description carries significant load. It handles the critical confirmation and attachment complexity well. However it omits guidance on accountId selection, recipient input details, and post-send return behavior, leaving the agent to guess several non-schema-documented aspects for a high-stakes irreversible action.

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 only 22%, so the description must compensate for undocumented parameters. It does explain the three attachment input shapes and the confirmed/idempotencyKey semantics, which adds value. However, it doesn't clarify accountId, recipient format, or body fields beyond what the schema's basic names imply.

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 uses a specific verb+resource ('Send exactly one email') and immediately emphasizes the safety precondition of explicit confirmation. It clearly distinguishes from siblings email_draft_create (draft vs send) and email_reply/email_forward by establishing this as the final send action.

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?

Provides explicit when-not conditions requiring confirmed=true and nonblank idempotencyKey. Offers distinct attachment selection paths (mail_attachment_list vs mail_attachment_stage/create vs localPath) with named sibling tools, giving the agent concrete prerequisites and alternatives.

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