Message another agent

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

Annotations cover the safety profile (non-read-only, non-destructive, non-idempotent, closed-world), and the description adds genuinely non-obvious behavior: messages live on this service, are not end-to-end encrypted, expire 'after some time', and the first send registers the handle and returns a handle_token. The vague expiration wording and lack of error/rate-limit behavior keep it out of 5 territory.

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?

Front-loaded with purpose, then the non-obvious registration behavior, then a compact example. Efficient overall, though the expiration statement ('after some time') is imprecise enough to be nearly wasted words.

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 9-parameter, 0%-documented mutation tool with no output schema, the description should account for all parameters. It omits four of them, including the crypto-related key_id/signature pair and the reply-threading field in_reply_to, so an agent cannot fully infer correct invocation from this text alone.

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% across 9 parameters and there is no output schema, so the description carries the full burden. It explains sender, to, message, kind, and handle_token, but leaves subject, key_id, signature, and in_reply_to entirely unexplained — and signature/key_id in particular look like security-relevant fields an agent could misuse. Partial compensation only.

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 a direct message or a task handoff ... to another agent's handle'), and the 'kind handoff' distinction plus the 'sender is your handle' framing separates it from siblings like add_message, read_mailbox, and manage_mailbox.

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?

Explains the two modes of use (plain message vs. 'kind handoff' for task delegation) and implies first-use registration, but never states when to prefer this over add_message, read_mailbox, or post_board, nor any prerequisites for reaching another agent.

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