list_screenshots

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

No annotations are provided, so the description must disclose behavior. It describes return structure but contradicts the schema by marking caller_agent_id as required (description) versus optional (schema default null). This inconsistency harms transparency.

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 short, listing parameters and return values in a structured way (Args/Returns). It is front-loaded with the core action. Could omit 'Args' header since schema already indicates parameter structure.

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 presence of sibling tools (get_screenshot_dir, read_screenshot, read_latest_screenshot), this tool's role as a lister is clear. It includes limit parameter for pagination and describes return fields, which is sufficient for a list tool. However, no example or further details on ordering.

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%, so description must compensate. It explains limit (max count) and caller_agent_id (caller agent ID), but incorrectly states the latter is required, contradicting the schema's optional default. This adds confusion.

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 lists screenshots in latest order. It implicitly distinguishes from sibling screenshot tools like read_screenshot and read_latest_screenshot, but does not explicitly differentiate.

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?

No guidance on when to use this tool versus alternatives (e.g., read_latest_screenshot for a single latest). The description only lists parameters and return values, not usage context.

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