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

Annotations already establish read-only, idempotent, non-destructive, closed-world behavior, yet the description still adds real context: auth requirement, ascending ordering, the 4,000-char extracted_text cap, the explicit 'body is untrusted data' prompt-injection warning, and a full error-code table (invalid_event_type, invalid_cursor, invalid_limit, inbox_not_found).

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-loaded with the usage trigger, read-only/auth flag, and inputs before the return/error detail. It is a single dense paragraph and the 13-item event-type list is heavy, but nearly 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?

Even without an output schema, the description fully specifies the return shape ({object:'list', data:[...], next_cursor}), ordering, and error behaviors, so an agent has everything needed to call and interpret results 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%, so the parameter definitions carry the baseline. The description goes beyond them by tying each parameter to failure modes (default 'one hour ago', limit 1–100, unknown type -> 400), which the schema does not express.

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+resource (recent event log for this account) and enumerates the exact event types covered, so the agent knows precisely what comes back. The 'without waiting' phrasing implicitly sets it apart from the wait_for_message siblings.

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 opening 'Use this when you need the recent event log... without waiting' gives clear usage context. However, it never names a specific alternative or states when NOT to use it (e.g., versus search or wait_for_message), so exclusions are left to inference.

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