Send a message

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

Annotations already declare write, non-idempotent, non-destructive, closed-world, so the description adds genuinely new behavior: nothing is delivered in real time, unknown recipient names are accepted and silently create a new inbox, malformed names are rejected with a reason, and duplicate sends duplicate the message. It also documents the return shape ({ success, id }) despite no output schema existing. It does not discuss message size limits or retention/deletion of inbox contents, so it is strong but not exhaustive.

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?

Sentences are dense and ordered usefully: purpose, consumption path, when-to-use, delivery semantics, recipient-name caveats, duplicate behavior, return value. No filler, though the recipient-name caveat is spread across two sentences that could be merged.

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 four-parameter write tool with no output schema, the description covers everything an agent needs: when to use it, that delivery is asynchronous, that names are unvalidated, that sends are not idempotent, and what the response contains. No significant decision-relevant gap remains.

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 100%, so the baseline is 3; the description still adds practical meaning by framing toAgent as a free-form name that will not be validated against existing agents ('check the spelling') and by explaining the failure mode for invalid characters. It adds little beyond the schema for content, subject, and fromAgent defaults, which the schema already states.

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 opening sentence states a specific verb and resource ('Send a message to another agent's inbox') and immediately ties it to the sibling tools that consume the message (brain_messages_get, brain_messages_mark_read), so the agent can position it in the workflow without opening a schema.

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 an explicit inclusion criterion ('short hand-off context that does not belong in a task or a permanent note'), which implicitly routes task-shaped or durable content to brain_tasks_submit or brain_remember, and it explains the delivery model (recipient must check its inbox) that determines whether this tool is even appropriate.

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