message_send

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

With no annotations, the description carries the full burden and does disclose the key behavior: the message is persisted, and wake=true conditionally starts a new turn. However, it omits side effects like delivery guarantees, recipient state requirements, or whether failures can occur silently.

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?

Two concise sentences with no filler. The core action is front-loaded, and the wake behavior is presented as a conditional add-on, making the tool's behavior easy to parse quickly.

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?

The tool is a mutation with no annotations, no output schema, and 0% parameter coverage. The description does not explain return values, error conditions, or how this differs from the sibling 'send' tool, leaving an agent with notable gaps when deciding to call it.

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%, so the description must compensate. It clarifies wake's conditional behavior and the general notion of an attributed message, but gives little explicit semantics for to_agent_id and message beyond their names.

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 ('Persist') and resource ('attributed message to another agent'), making the core action clear. It does not explicitly distinguish itself from the sibling tool 'send', but the persistence and attribution framing separates it at a basic level.

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 description explains the wake=true behavior but gives no guidance on when to use this tool versus alternatives like 'send' or 'message_ack'. There is no mention of prerequisites, conditions, or cases where a sibling would be more appropriate.

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