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

Annotations already disclose destructive=true and openWorld=true. The description adds that compose reuses an open thread with the recipient, but it does not explain what destructive commands affect, whether actions are reversible, or how idempotency and dry_run behave. For a tool containing quarantine, spam classification, and sender-policy mutations, this is a significant behavioral gap.

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 description is two sentences, front-loaded with the capability list and then compose constraints. There is no wasted wording, though the brevity is arguably too extreme for a 29-parameter tool.

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 12-command, 29-parameter destructive tool with no output schema, the description is far too thin. It does not explain return values, command-specific prerequisites, idempotency, dry_run semantics, or the behavior of most mutating commands.

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 59% across 29 parameters. The description states compose requires inbox_id, to, subject, and body and broadly maps action categories to command families, which adds some meaning beyond the schema. But command-specific parameter requirements remain largely undocumented for most of the 12 commands.

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 names the resource and several verbs (compose, reply, reserve attachments, triage, set sender policy, read state, contact linkage), so the agent knows it is an inbox action surface. However, it omits several enum commands such as mark_handled, request_human, release_to_agent, mark_quarantine, classify_spam, and send_reply_test, and it does not clearly distinguish this tool from siblings like nitro_send_message or nitro_inbox.

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?

There is no explicit when-to-use or when-not-to-use guidance, and no alternatives are named. The only conditional instruction is that compose requires inbox_id, to, subject, and body; the agent must infer how to choose among the 12 commands and against sibling tools.

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