send_email

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

No annotations are present, so the description carries the full burden. It usefully discloses the critical approval-gating behaviour and the Apple Mail transport. It does not disclose that sending is irreversible, whether the message is dispatched immediately or queued, or how failures surface — meaningful gaps for a destructive, outbound action.

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 sentences, front-loaded with the action and followed immediately by the gating constraint. Every clause carries weight with no redundancy.

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 outbound action with no annotations and no output schema, the description covers the approval gate but leaves the post-send behaviour unspecified. It also misses the opportunity to route the agent to preview_send or queue_email_for_approval when approval is absent, so it is adequate but incomplete for the risk level.

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 60%; 'to', 'from', and 'user_approved' are documented in the schema, while 'text' and 'subject' are not. The description references 'this exact recipient, subject, and body', adding the semantic that the three required values must correspond to a single user-approved draft, which is meaningful but not a full parameter treatment.

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 using Apple Mail'), so the agent immediately knows the action and transport. However, it does not differentiate from relevant siblings such as preview_send or queue_email_for_approval, which perform adjacent send-related functions, leaving the agent to infer the distinction.

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 a clear, explicit precondition: call only after the user approved this exact recipient, subject, and body. This is strong usage context. It stops short of naming alternatives (preview_send, queue_email_for_approval) for cases where approval has not yet been granted, so it is clear but lacks exclusions.

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