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

Annotations already declare destructiveHint=true, but the description goes further by explaining the concrete consequence: '🔴 **This sends real email to everyone in the thread and it cannot be recalled.**' and the shared-account caveat. This adds behavioral context that the structured annotations do not provide, and it does not contradict them.

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?

Two sentences, both information-dense and front-loaded. The critical warning about irreversibility is placed early, and the alternative is named concisely. No filler or redundancy; every clause earns its place.

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?

Given the tool's complexity (9 params, nested objects, output schema present), the description covers the key behavioral, safety, and selection aspects. It mentions the return values (message_id and thread_id) and the shared-account risk. The schema handles parameter details and the output schema covers return structure, so nothing essential is missing for correct invocation.

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 fully documents all 9 parameters. The description adds value by clarifying the scope of recipients, but that is a behavioral distinction, not parameter-level meaning. It doesn't elaborate on any specific parameter beyond what the schema already states, so the 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?

The description uses a specific verb ('Replies to') and a clear resource ('one message and every other recipient on it'), and explicitly distinguishes it from the sibling `post_agentmail_inbox_message_reply` by noting the difference in recipients. This leaves no ambiguity about what the tool does or how it differs from alternatives.

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?

The description gives explicit guidance on when to use this tool versus the safer alternative: 'Use `post_agentmail_inbox_message_reply` when only the sender should receive the answer — that is the safer default'. It also warns about the shared-account context, which is crucial for decision-making. This fully covers usage selection.

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