save_screenshots

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

The description adds critical behavioral details beyond annotations: it writes to the local filesystem (side effect) and returns metadata without base64. This complements the destructiveHint and readOnlyHint annotations, making the tool's behavior transparent.

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?

Two sentences with no filler. The first sentence states action and outcomes; the second provides a usage alternative. Every word earns its place.

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?

For a tool with no output schema, the description covers the return format (metadata). It explains the core function and provides a useful sibling reference. Minor omission: no mention of default resolution or potential file overwrite, but overall complete given the low complexity.

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 all parameters described. The description provides context that the tool writes files and returns metadata, but does not add specific parameter semantics beyond what the schema already offers. Baseline of 3 is appropriate.

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 defines the tool's action (export screenshots and write to filesystem) and resource (multiple nodes). It distinguishes from the sibling get_screenshot by specifying that this tool saves to disk and returns metadata, not base64.

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 directs the agent to use get_screenshot when image data is needed in memory, providing a clear alternative. It does not cover all possible alternatives (e.g., export_frames_to_pdf) but is sufficient for basic guidance.

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