Send Email

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It explicitly states the action is real and irreversible, with no intermediate confirmation, and warns against autonomous invocation – critical safety context for a mutating email operation. While it doesn't mention potential failures or rate limits, the core irreversible behavior and consent requirement are clearly disclosed.

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 three sentences, each earning its place. The first establishes purpose and irreversibility, the second gives hard usage constraints, and the third handles threading. It is slightly longer than necessary but front-loads the most critical safety information, making it structured and readable.

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 an irreversible tool with 7 parameters, threading, attachments, and multiple recipients, the description covers the essential operational context: user consent, no retry, and threading mechanics. Attachments and return values are handled by the schema and output schema, so the description is sufficiently complete for correct invocation in most cases.

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 coverage is 100%, so all parameters are documented in the schema. The description adds value beyond the schema by explaining the semantic meaning of in_reply_to (pass the message_id from read_email or get_thread) and references (full header for multi-message threads), which helps an agent understand how to correctly fill these optional fields rather than just listing them.

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 'Envoie un email via le compte iCloud configure' – a specific verb, resource, and scope. It immediately distinguishes itself from the sibling save_draft by stating this is a real, irreversible action with no draft or server-side confirmation, so an agent can tell it apart without inspecting other 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 gives explicit, actionable guidance: use only after the user has validated the exact content, never call on your own initiative, never in response to an email read, and never retry a confirmed send without re-asking. It also provides the condition for replying in a thread (passing in_reply_to with the original message_id from read_email or get_thread), leaving no ambiguity about when and how to use the tool.

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