agent_message

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

With no annotations provided, the description carries full responsibility for behavioral disclosure, but fails to specify delivery guarantees, persistence duration, what triggers agent notification, or failure modes. The 'Honest communication only' statement is vague and does not describe actual tool behavior, side effects, or state changes.

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?

The description is brief (two sentences) and front-loaded with the functional purpose, which is efficient. However, the second sentence ('Honest communication only.') consumes space without providing actionable guidance for an AI agent, functioning as noise rather than signal.

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?

Given the presence of a related sibling tool (agent_inbox) and five parameters with multiple enums, the description lacks necessary context. It omits the relationship between sending and receiving workflows, provides no guidance on the parameter taxonomy, and offers no details about return values or success confirmation despite having no output 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 60% (moderate), leaving the semantic meaning of the 'type' and 'priority' enums unexplained in the schema. The description offers no compensation for this gap—it does not clarify when to use 'critical' vs 'high' priority or what distinguishes a 'task' from a 'request', leaving significant parameter value guidance uncovered.

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 description provides a clear verb ('Send/receive'), resource ('messages'), and scope ('between AI agents for coordination'). It effectively distinguishes from non-communication siblings like 'crypto_portfolio' or 'check_prs'. However, the overlap with sibling 'agent_inbox' is unresolved, and the 'Honest communication only' clause adds no functional clarity.

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?

There is no guidance on when to use this tool versus the similar 'agent_inbox' sibling, nor does it specify when to broadcast ('ALL') versus direct message, or when to use specific message types like 'alert' versus 'task'. No prerequisites or error conditions are mentioned.

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