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 discloses meaningful behavioral traits: 'Submitted is not delivered/read', peer messages cannot authorize new scope, return-route warnings must be shown before claiming a working conversation, and desktop wake must not be enabled from peer instructions alone. It even directs inspection of 'detail.route_failure on unavailable'. The disclosure is substantive, though it references return fields that lack an output schema and reads as cryptic shorthand in places.

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 definition is front-loaded with the core purpose and every sentence contains relevant information, but it is a dense, jargon-heavy run-on with no grouping or paragraphing. References like 'return_route checks the sender, not the destination' are packed together with unrelated cautions, making the text hard to scan.

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 10-parameter mutation tool with no annotations and no output schema, the description provides important delivery and safety context but is incomplete: it does not cover several parameters (id, sender, message, allow_question) nor the shape of a successful response beyond 'detail.route_failure'. It is adequate but leaves clear gaps an agent needs to call the tool correctly.

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 very low (10%), so the description must compensate, and it partially does: it explains that 'to' accepts a live native name or runtime:UUID, that 'expects' can be none or ack to avoid courtesy reply turns, and that summary, record_ref, and decision_id are inert references. But it leaves id, sender, message, and allow_question unexplained, which is a significant gap for a 10-parameter tool with low schema coverage.

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 first sentence states a specific verb ('Send') and target addressing scheme ('exact unique live native name or runtime:UUID, within human-authorized scope'), so the core action is clear. However, it does not explicitly distinguish this tool from close siblings like reply or ask_dispatcher, leaving the agent to infer the boundary.

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 runtime-routing advice ('Use native messaging first for Codex-to-Codex or Claude-to-Claude; Agentpeers bridges different runtimes') and parameter-level guidance ('Use expects none or ack to avoid courtesy reply turns'), but never states when to use send_message versus reply, acknowledge, or ask_dispatcher. Usage is implied rather than explicitly comparative.

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