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

Annotations already declare readOnlyHint=true, so no contradiction. The description adds valuable behavioral context: it states the tool returns event history and that the status reason is included for undeliverable messages. It also discloses that include_output is off by default because 'rendered email can be large,' which signals performance implications beyond the schema.

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 three sentences, front-loaded with the core purpose ('Trace delivery in one call'). Every sentence earns its place: it covers invocation modes, return content, and the include_output option, with no fluff or redundancy.

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 read-only trace tool with four parameters and no output schema, the description adequately explains what is returned (matching messages with event history and status reasons) and key parameter semantics. It doesn't detail pagination or error cases, but the limit parameter and read-only nature make it sufficiently complete for an agent to call correctly.

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% with descriptions for each parameter, so baseline is 3. The description adds meaning: it clarifies mutual exclusivity of message_id/trace_id, explains that trace_id can span several messages, and describes the default behavior of limit and include_output with rationale. This exceeds the schema alone.

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 states a specific verb ('Trace') and resource ('delivery') and explains the two mutually exclusive ways to invoke it (message_id or trace_id). It clearly distinguishes from sibling tools like get_message or get_message_history by framing this as a one-call delivery trace that returns event history with status reasons.

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 parameter usage: 'Give EXACTLY ONE of message_id or trace_id' and explains the difference between a single message and a trace spanning multiple. It also indicates when to set include_output. However, it does not explicitly compare to alternatives like get_message_history, though the 'in one call' framing implies a distinction.

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