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

Annotations already declare non-read-only, idempotent, non-destructive; the description adds only the ownership constraint "an item you own." It is silent on the fact that messages are dispatched to an external issuing network via passes, on the required idempotency key for agents, and on whether the send is reversible or delivered asynchronously.

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?

A single nine-word sentence with no filler, but the brevity crosses into under-specification rather than efficiency. The new-vs-reply distinction is at least front-loaded.

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?

This is a 9-parameter mutation tool with a nested contact object and no output schema, so the description carries a lot of explanatory burden. Key questions an agent needs answered — how the recipient is identified, what the access_token grants, what a successful send returns — are left entirely to the schema.

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 56% and the description contributes nothing to close that gap. The rich schema notes on key, pass, item_id, access_token and idempotency_key do the work, while undocumented parameters like body, subject, message_id and the nested contact object get no help from the description.

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?

"Start a conversation, or reply on an item you own" conveys two modes of a send operation, but never states plainly that it sends a message, to whom, or over what channel. No sibling tool overlaps in function, so differentiation is not an issue, but the purpose remains only loosely specified.

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 new-vs-reply branching is implied (start a conversation vs reply on an item), which is usable guidance. However there are no prerequisites, no mention of when a pass/key/contact is required versus an access_token, and no exclusions or alternatives.

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