send_message

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 meaningful behavior: 'it runs nothing there' (no remote execution side effect), that it returns id and seq, and that delivery is tracked via message_status on the joxo_more team. It stops short of permissions, rate limits, blocking vs async delivery, or failure behavior, so it is good but not complete.

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?

Very compact and front-loaded, with no filler sentences. However the semicolon-packed phrasing ('delivery: message_status (joxo_more team)') reads as shorthand rather than clear prose, costing comprehension for its brevity.

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?

No output schema exists and the description compensates by stating the return shape (id and seq) and how delivery is observed. For a 5-parameter, zero-required message tool, the essential calling information (payload options, reply targeting, return values) is present, so it is adequately complete.

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 only 60%, so the description usefully clarifies the payload alternatives ('summary plus details, or body') and the in_reply_to semantics (an id or #seq), which the bare schema does not convey. It leaves target_device's interaction with the alternatives unstated, but it adds real meaning beyond the schema.

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 (send an update or request) and names the recipients (collaborators or one target device), plus the key negative that it 'runs nothing there'. It does not, however, distinguish itself from siblings like tell_people or ask_people, which occupy very similar territory, so an agent cannot fully route between them from this text alone.

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?

Gives implied usage ('send an update or request', and how to answer with in_reply_to), which is enough context to attempt a call. But it never says when to prefer send_message over tell_people or ask_people, nor any exclusions or prerequisites, leaving the sibling choice to inference.

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