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

Annotations already declare readOnlyHint and openWorldHint=false, so the safety profile is covered. The description adds real behavioral context beyond the annotations: the 4000px threshold where preview truncates, and the warning that size=full may exceed what vision models can accept.

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?

Front-loads the core action in the first sentence, then adds scoping and vision-limit caveats. Three sentences, all earning their place, with no redundant restatement of the schema enum.

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?

With no output schema, the description correctly explains what comes back (the image) and its practical limits, plus the sibling that supplies section metadata. Adequate for an image retrieval tool with full schema coverage, though return format details (e.g., resolution/type) are not addressed.

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%, so the baseline is 3, but the description adds meaning the schema lacks: preview yields only the first screen above the fold, and full returns the whole page at the risk of exceeding vision-model input limits. The size tradeoff is therefore clearer than the schema alone.

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?

States a specific verb+resource ("Get the screenshot itself") and immediately distinguishes itself from the metadata-oriented sibling by noting that getScreen returns section y-offsets instead of the image. An agent can tell what this returns versus neighboring tools without opening a schema.

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?

Gives concrete guidance on when to pick preview vs size=full (above-the-fold vs whole page, vision-model limits) and routes section-level needs to getScreen. It stops short of an explicit "when to use this tool instead of get_screen" statement, but the context is clear.

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