poll_changes

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

Beyond the annotations, the description adds valuable behavioral context: repeated polls retain the pending observation ID, and visual changes are explicitly not proof of a new incoming message. This helps the agent interpret results correctly, though it does not clarify the non-read-only implication from readOnlyHint=false.

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?

Three sentences, all informative. The main return value is front-loaded, and each additional sentence earns its place by clarifying visual-change semantics and poll behavior. No wasted words.

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 what is returned, when to call it, and how to interpret results. It does not define 'pending observation ID' or address the potential side effects implied by readOnlyHint=false, but these are minor given the single parameter and simple nature of the tool.

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 0% and the description never mentions session_id. With only one parameter, its purpose is somewhat inferable from the tool name and context, but the description does not explicitly add meaning to the schema, so it fails to compensate for low coverage.

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 a specific action ('Return') and resource ('pending before/after chat images and raw OCR'), plus the timing condition ('after the polling interval'). It is distinct enough from siblings like get_status or acknowledge_observation, though it does not explicitly name alternatives.

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 implies when to use the tool ('after the polling interval') but gives no explicit guidance on when not to use it or which sibling to choose instead. Usage context is present but underdeveloped.

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