browser_screenshot

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds a genuine behavioral fact not in annotations: the image is both returned to the model and persisted to disk. It omits where the file lands and what format, which caps it below 5.

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?

A single front-loaded sentence that loses no words and immediately states scope and return behavior. Nothing redundant or padding-like.

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 carries the return-value burden and does so partially, explaining that an image comes back and is saved to disk. It leaves unspecified the save location, image format, and whether the returned image is inline, which an agent might need for follow-up steps.

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 75%, so ref/text/selector are already documented in the schema; the description adds only the page-vs-element framing. The boolean fullPage has no description in either place, leaving one parameter's semantics unexplained.

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+resource ('Screenshot of the page (or one element)') and clarifies scope (whole page vs. a single element), which lets an agent distinguish it from browser_snapshot or browser_get_text. It does not name those siblings explicitly, so it falls short of a 5.

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?

Usage is only implied by 'The image is returned so you can see it,' which suggests reaching for this when visual output is needed rather than text. No when-to-use/when-not or comparison against browser_get_text or browser_snapshot is given, so the routing decision is left to inference.

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