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

Annotations only supply readOnlyHint=false; the description carries the real behavioral burden, disclosing that fleet-line/self conversations degrade to plaintext with a concrete result shape (`encrypted: false, reason: "fleet_plaintext"`) and that true E2E requires published recipient keys. That is exactly the non-obvious side effect an agent needs before sending.

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-loads the action and the encryption rule, then the addressing rule, then the thread feature — a sensible ordering. Some clauses ('exactly like the mosadd app', 'unlike WhatsApp/Telegram') are comparative color rather than operative instruction, plus heavy capitalization, which trims it below full marks.

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 usefully sketches the result field for the plaintext case and covers the encryption precondition, so an agent can call it correctly. It omits delivery/failure behavior (rate limits, what happens if keys are missing) and anything about attachments, which keeps it short of 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 100%, so baseline is 3; the description goes beyond it by explaining what thread_label actually does (named thread per contact, multiple threads allowed, default when omitted) and by reinforcing that `to` is an identity_id requiring lookup. The reply_to_id parameter is left entirely to 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 and resource ('Send a direct message via mosadd mDM') and immediately clarifies the encryption scope that distinguishes this from mDM_send_unencrypted and mDM_send_as_agent. It never names those siblings explicitly, so the differentiation is inferential rather than explicit.

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 clear pre-call guidance: resolve the recipient via mDM_list_contacts and ensure the recipient has published keys before expecting encryption. It does not state when to prefer mDM_send_as_agent, mDM_send_unencrypted, or mDM_send_file instead, which are the closest alternatives in the sibling list.

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