What this key has done

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

Annotations already declare this is read-only, idempotent, and non-destructive. The description adds valuable extra behavior: message bodies are never stored in the audit log, which matters for privacy and for what can be reported afterward.

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 economical sentences: it states the core behavior, adds an important caveat, and closes with a direct use case. Every sentence earns its place with no 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?

With no output schema and no parameter descriptions, the description should explain what the agent gets back and how to use the optional parameters. It explains the logged fields conceptually but leaves pagination, filtering, and the meaning of 'since' and 'cursor' undefined, so an agent cannot reliably construct a correct call.

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?

The input schema has 0% description coverage, and the description does not compensate by explaining limit, since, cursor, or operation. It mentions 'operation' as a logged field, not as a filter parameter, and gives no guidance on pagination or filter formats.

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 ('Return') and resource ('log of API actions') and enumerates the meaningful fields: which key, operation, parameters, and result. The title reinforces the audit-log purpose, and this is clearly distinct from sibling tools like get_usage, list_bounces, or list_messages.

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 gives a clear use case: 'Use it to report exactly what was done.' This tells the agent when the audit log is the right tool, though it does not explicitly rule out alternatives or mention sibling tools.

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