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

Annotations already declare this tool read-only and non-destructive, so the safety profile is covered. The description adds useful behavioral context beyond the annotations: it does not render the page, and it returns source images with metadata. This gives the agent a clearer mental model of what invocation will and will not do.

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 two sentences with no wasted words. The core action is front-loaded, and the comparison to screenshot is placed second where it helps decision-making without bloating the description.

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 single-parameter, read-only tool with no output schema, the description is complete enough. It explains what the tool returns, how invocation behaves, and how it differs from a likely sibling. Nothing an agent needs to select or call this tool correctly is missing.

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 schema already documents the single url parameter with 100% coverage, so heavy description compensation is unnecessary. The description reinforces that the URL identifies a page to harvest images from, but it adds no new parameter-level detail such as formats, defaults, or constraints. Baseline 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 states a specific verb ('Harvest') and resource ('a page's images with their metadata'), and explicitly distinguishes itself from a screenshot by noting it returns source images rather than a rendered picture. This makes the tool's purpose unmistakable and differentiates it from the sibling tool screenshot.

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 gives clear guidance on when this tool is preferable to a screenshot: it is cheaper and returns source images rather than a visual representation. However, it does not explicitly mention when not to use it or name other alternatives among the siblings, so some selection context is left implied.

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