screenshot

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

With no annotations, the description must carry the behavioral burden, and it does disclose real traits: high token cost, that region coordinates are in previous-screenshot pixels, and that marks derive from the last snapshot (a state dependency an agent could easily get wrong). It omits what is returned (image format/attachment), and how the `screen` parameter behaves in multi-monitor setups, leaving notable behavioral gaps.

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?

Extremely compact and front-loaded: the most decision-relevant fact (last resort, expensive) comes first, followed by the cheaper per-parameter alternatives. The semicolon-chained, telegraphic style wastes nothing but is slightly terse enough to be ambiguous on first read.

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?

Five optional parameters, zero schema descriptions, no annotations, and no output schema — the description is the only documentation, and it leaves `screen` and `max_side` (including the 1280 default's effect on image fidelity) entirely unexplained. Return value need not be covered given no output schema, but the missing parameter coverage and absent output-format hint leave the agent under-informed about a tool that costs many tokens.

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 description coverage is 0%, so the description is the only source of parameter meaning, yet only 3 of 5 parameters are covered: ref (crop around an element), region (format and coordinate reference frame), and marks (draws refs from last snapshot). These additions are genuinely valuable — the coordinate-frame note in particular — but `screen` and `max_side` are never explained, so it only partially compensates.

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 the resource plainly ("image of your screen") and immediately frames its role as a costly fallback ("Last resort ... costs many tokens"), which lets an agent distinguish it from snapshot-style siblings. The verb is implicit rather than an explicit imperative, and the tool name/title say the same thing, but the added cost framing and the ref-vs-full-capture distinction make purpose unambiguous.

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?

"Last resort" is an explicit usage ranking: try other tools first, capture pixels only when necessary. It also gives a cheaper path ("ref=crop around an element (cheap, sharp)") versus a full-screen capture. It does not name which sibling to prefer or state hard exclusion conditions, so it stops short of a 5.

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