agent_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 so well: it discloses the allowlist authorization gate, the local credential-store identity model, and the critical privacy caveat that the relay uses server-held keys and can read content (not end-to-end encrypted). It stops short of delivery/return semantics or failure behavior on send.

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?

Four tightly packed sentences, front-loaded with the core action before the authorization and privacy constraints. Every sentence carries distinct, decision-relevant information with 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?

For a no-annotation, no-output-schema mutation tool, the description covers authorization, identity, and the encryption model, which are the highest-risk unknowns. The one remaining gap is what a successful send returns or confirms, which the agent must infer.

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 100%, so the schema already documents to_did format, message text, and the thread_id constraint. The description's relay-readability note duplicates the message parameter's own schema description, adding no new parameter-level meaning. Baseline 3 applies.

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 and resource (send a message) plus the addressing scheme (by DID), which cleanly separates it from channel-oriented siblings like agent_post_to_channel and fan-out tools like agent_broadcast_task. An agent can identify the operation without opening the schema.

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?

Explicitly states the gating condition: it is off by default and refused unless the recipient is in VOIDLY_MCP_RELAY_ALLOWED_RECIPIENTS, which is actionable when-to-use context. It does not, however, contrast this direct-message path with alternatives such as channel posts or broadcasts, so routing guidance is incomplete.

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