send_email

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

Beyond the destructiveHint annotation, the description reveals environment-dependent behavior: PROTONMAIL_SEND_DELAY_SECONDS queues the send and returns a cancelable id, with the option to call cancel_send. It also explains the return behavior (delivery confirmation immediately vs queued id), adding substantial context the annotation alone does not provide.

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 front-loaded with purpose, followed by usage guidance and behavior specifics. Every sentence earns its place: no fluff, no repetition of schema details, and it remains compact despite the tool's 16 parameters. The structure flows logically from what → when → edge cases.

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 complex send tool with 16 parameters and no output schema, the description covers all essential aspects: purpose, usage, failure modes, asynchronous behavior, and return types. It also leverages sibling context by positioning itself relative to create_draft and reply_to_email, making the overall tool selection and invocation straightforward.

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 100%, so the baseline is 3. The description does not add parameter-specific meaning; it focuses on tool-level behavior. Since every parameter is already well-documented in the schema, the description does not need to compensate, but it adds no extra semantic value.

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 opens with a specific verb+resource+scope: 'Compose and send a new outbound email through Proton Bridge SMTP.' It immediately distinguishes itself from siblings by explicitly naming create_draft and reply_to_email as alternatives, making its unique purpose unmistakable.

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 provides explicit when-to-use guidance ('one-shot messages that need no review') and names alternatives ('Prefer create_draft when...', 'reply_to_email when...'). It also states failure conditions (PROTONMAIL_ALLOW_SEND false, Bridge SMTP unreachable), giving clear operational boundaries.

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