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

With no annotations provided, the description carries the full burden. It discloses the lack of read/unread tracking server-side and instructs the agent to track its own last-seen timestamp, which is critical behavioral information. It also explains message visibility scoping (sub-key vs owner_key) and the pull-based nature. While it doesn't mention rate limits or explicit read-only status, the behavior is sufficiently covered for an agent to anticipate side effects.

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 information-dense but every sentence contributes meaning: the core function, the fallback context, visibility rules, and the tracking idiom. It is front-loaded with what the tool does, then adds necessary context. No filler or redundancy, and the structure flows logically from purpose to usage to caveats.

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?

The description covers the essential operational aspects: when to use, visibility semantics, and the lack of server-side state tracking. Since an output schema exists, the return format does not need to be explained in prose. For a message-fetching tool with visibility nuances, this description provides all the information an agent needs to call it correctly and interpret results.

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 detailed descriptions for each parameter. The description adds value by explaining the intended usage of `since` (track your own last-seen ts) and the auth model affecting what messages are returned, which goes beyond the schema text. It also references a sibling tool's pattern for consistency. This exceeds the baseline of 3 because it provides practical guidance not present in the schema.

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 clearly states the tool fetches messages sent via aanet_send_message, positioning it as a pull-based fallback to webhooks. It explicitly contrasts with webhook registration and names the specific verb 'fetch' with a concrete resource. This is distinct from sibling tools like aanet_get_activity, so an agent can immediately understand its unique role.

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 explicitly states the condition for use: 'when you haven't registered a webhook on the message event.' It also explains the alternative (webhook) and clarifies the visibility rules for sub-key vs owner_key, giving clear guidance on when to use it and what to expect. The mention of the 'same pattern as aanet_get_activity' for the `since` parameter provides cross-tool usage context.

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