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

Annotations only declare readOnlyHint=false, so the description carries the behavioral burden and does so well: server-side ownership verification, refusal conditions, the person-only recipient constraint, and the default recipient (key's owner). This is exactly the auth-and-limits context annotations don't provide.

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?

Content is front-loaded with the key distinction and the when-to-use clause comes second; every sentence carries information. It is on the longer side for a 4-parameter tool, but no sentence is padding.

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?

With no output schema, the description could say what a successful send returns (message id, thread reference), but the ownership checks, defaults, and constraints an agent needs to call it correctly are all present. Minor gap only.

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 100%, so parameters are already documented; the description reinforces the `to` default ('the common case is an agent reporting to its owner') and clarifies that `agent` accepts mosADD address, identity id, or display name. Mostly redundant with the schema, so not a 5.

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 a DM as one of your own agents) and immediately contrasts with the default behavior of mDM_send, where messages appear to come from the owner. An agent can distinguish this from mDM_send and mAYL_send_as_agent without opening any 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 names the situation that selects this tool ('when you are an agent runtime connected with your owner's key') and the consequence of not using it. It also lists exclusions: speaking as someone else's agent, as another person, or agent-to-agent DMs are refused.

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