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

Annotations already declare the write/idempotent/non-destructive profile, and the description adds genuinely non-obvious behavior: 'Queued is not delivered,' i.e. deferred rather than immediate delivery, plus mode/budget/approval preconditions. It stops short of saying anything about failure handling or what a queued message's lifecycle looks like.

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?

Three short sentences, no filler, with the scope and the critical 'queued is not delivered' caveat placed prominently. It is dense to the point of being telegraphic, but every sentence does work.

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 7-required-parameter mutation with no output schema, the description covers the important call preconditions and delivery semantics but leaves the parameter layer almost entirely undocumented. An agent could invoke it correctly only by guessing at several mandatory fields' meaning.

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 0% across 7 required parameters, so the description must carry the burden and largely does not. It only loosely gestures at share_approved ('share confirmation') and messages being 'shared'; conversation_id, text, materials, idempotency_key, client_message_id and expected_conversation_version are entirely unexplained anywhere.

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 description gives a specific verb+resource ('Queue a shared message') scoped inside a conversation grant, which is more precise than the bare tool name. It does not, however, name or distinguish itself from siblings like ack_conversation_message or complete_conversation_draft, so the agent must 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 lists prerequisites for use ('requires current automatic mode, remaining message budget and share confirmation'), which is real gating context, but it never states when to choose this tool over an alternative sibling or what happens if the preconditions are unmet.

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