send_message

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

With no annotations, the description carries the burden and handles the single most important behavioral fact: delivery is asynchronous and happens on the recipient's next check-in, typically at the start of its next turn. It does not cover failure modes (unknown target, offline session) or whether self-messaging is permitted.

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 purpose sentence followed by a compact args list; every line earns its place. Slightly verbose in the delivery-timing clause, but no filler.

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?

Output schema exists, so return values need not be described, and both parameters plus the async delivery model are covered. Missing only edge-case behavior (nonexistent target, queueing limits) that an agent might want before calling.

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 compensate, and it largely does: `to` is defined as the session name 'wie in list_agents angezeigt' (a real usability clue), and `text` is characterized as task/question/information. Only the format details for `to` (exact matching rules) remain implicit.

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+resource ('Sendet eine Nachricht an eine andere registrierte Agent-Session') and adds delivery semantics (the target sees it at its next check_inbox). It does not, however, draw a boundary against the `reply` sibling, which sends messages to a related session — an agent must infer which is correct.

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?

Usage is implied rather than stated: the mention that the target sees the message 'beim naechsten Aufruf von check_inbox' tells the agent this is an asynchronous, fire-and-forget send. There is no explicit when-to-use-this-vs-`reply` guidance or statement of preconditions (e.g., target must be registered/alive).

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