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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, covering the safety profile. The description adds the return-type trait ('viewable image') and the source of the key parameter, which is genuine context beyond the annotation hints. No contradiction with annotations.

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, each earning its place: the first states action and output type, the second states the data-source flow. Purpose is front-loaded and there is zero filler.

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 simple three-parameter fetch with rich annotations, the description covers purpose, output format, and the input-flow. The remaining gaps — the precise delivery format of the image and the meaning of the two ID parameters — would improve it but are not critical for a correct call.

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 only 33%, so the description must compensate. It meaningfully explains screenshotKey's provenance (from a step in get_play_status), but projectId and scriptRunId receive no documentation in either the schema or the description; their names are self-explanatory, which prevents a lower score.

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 ('Fetch') and resource ('a screenshot captured during a play') and clarifies the output is a viewable image. The play-context framing distinguishes it from the many other get_* siblings, none of which deal with screenshots.

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?

Sentence 2 gives clear when-to-use context: this tool consumes a screenshotKey produced by get_play_status, establishing the prerequisite call flow. It stops short of explicitly naming alternatives or exclusions, but no sibling offers a competing screenshot-fetching path, so the omission is minor.

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