send_message

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

Annotations already declare readOnlyHint=false and destructiveHint=true; the description adds the reason that matters to an agent — the message reaches a real person and cannot be unsent. That is genuine context beyond the annotation flags, though nothing is said about delivery failure or confirmation behavior.

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 lines, front-loaded with the action and the risk, then a compact Args block. Every sentence earns its place and nothing is padded.

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 two-parameter mutation tool with no output schema there is little to explain, and the description covers purpose, risk, and both parameters. It could note the expectation after sending (e.g., that delivery is asynchronous or unconfirmed), but nothing essential is missing.

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%, so the description carries the full burden and largely does: it explains that "to" accepts a phone number or Apple ID and how to obtain it, and that "text" is the message body. Naming the accepted identifier formats is the key detail the bare schema lacks.

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 iMessage"), which is precise enough to separate it from compose_email or notify without opening the schema. It does not name a sibling explicitly, so it stops short of the top mark.

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?

Gives actionable routing guidance for the ambiguous case: resolve a name to a handle via find_contact before calling. The irreversibility warning also sets the bar for when to be cautious. It never states when to prefer compose_email or notify instead, so it is clear context without exclusions.

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