Poll viewer commands

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

With no annotations, the description carries the full burden. It discloses that the tool 'drains queued interact commands,' indicating it consumes/mutates state. However, it does not describe the response format, error conditions, or consequences of calling it, leaving gaps.

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 a single concise sentence that clearly communicates the tool's internal purpose and disallows direct agent use. Every word 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?

Given the tool is explicitly marked as internal with a 'not for direct agent use' warning, the description adequately tells an agent to avoid it. It lacks details on triggering conditions or outcomes, but for an internal tool intended to be invisible, this is acceptable.

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 provides full descriptions for both parameters (document_id and view_uuid), achieving 100% schema coverage. The description adds no additional meaning about parameter usage, so it relies on the schema, which is sufficient.

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 specifies that the tool 'drains queued interact commands' for the viewer widget, providing a clear verb and resource. It is marked 'Internal' which differentiates it from agent-facing tools, though it does not explicitly distinguish it from sibling poll_document_view.

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 'Not for direct agent use,' which is a clear when-not-to-use exclusion. It also labels the tool 'Internal,' reinforcing that agents should avoid directly invoking it. This satisfies the guidelines criterion strongly.

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