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

The annotations already declare non-read-only, open-world, non-destructive, so the description's job is to add what those hints cannot: it discloses the authorization scope constraint, the approval rule for sensitive content, idempotency behavior via message_id reuse, and critically that "delivery is storage, not proof of reading or execution." That last line prevents a very common false assumption. It lacks failure/error behavior and size limits, keeping it at 4 rather than 5.

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?

Four short sentences, no filler, and the scope constraint plus the security warning are front-loaded ahead of the mechanical guidance. Each sentence carries a distinct fact: scope, safety, idempotency, delivery semantics.

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?

There is no output schema, so the description need not describe return values, and the delivery/retry semantics are well covered for a mutating open-world tool. Still missing for correct invocation: how participant_token is obtained, what happens when delivery fails or the token is invalid, and any message size/rate constraint.

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 0%, so the description must carry all three parameters. It handles message_id well by defining both its uniqueness constraint and its retry-reuse contract, which is the non-obvious one. participant_token and text receive no explanation at all — where the token comes from and whether text is plain or formatted is left entirely to inference.

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 verb+resource is clear: send text as a message to a collaborating agent, and the sibling set (read_agent_messages, invite_agent_participant, join_agent_session) makes the send/read contrast obvious. The qualifier "within your human-authorized collaboration scope" is a policy statement rather than a sharper definition, and the description never says the message goes to a session participant, which is why it stops short of a 5.

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 gives two concrete operating rules: do not send credentials or private files without approval, and use a unique message_id that is reused on retries. What it does not give is when this tool is the right choice relative to siblings (read_agent_messages, access_hosted_inbox) or any precondition such as needing an active session from create_agent_session/join_agent_session. Usage is implied rather than differentiated.

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