screen_time

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

With no annotations supplied, the description carries the full behavioral burden and does deliver real context: the device source needs no setup, apps iOS keeps resident or for calls count less and appear under 'background', while the mac source requires Share Across Devices and covers the trailing `days` window. That provenance detail is genuinely valuable and hard to get elsewhere. It still omits permission/auth implications, rate limits, and whether the two sources can disagree, so it is solid but incomplete for an annotation-free tool.

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?

It is compact, but the structure is weak: it opens with a sentence fragment listing outputs, and the source semantics arrive after the reader has already had to parse "estimated page swipes for the device vs the draft". Dense phrasing is used efficiently, but key routing information is not front-loaded.

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?

An output schema exists, so return values need not be spelled out, yet the description spends its opening enumerating outputs while leaving the modal question (when to use this over siblings) and the scope of `days` unresolved. For a two-parameter read tool this is adequate but not complete.

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 must carry the parameter meaning and it largely does, defining both source values in operational terms (device memory vs Mac sync) and tying `days` to a trailing window. The one gap is that `days` is described only in the mac branch, leaving ambiguous whether it also constrains the device source.

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 opening fragment describes what comes back (app usage, top apps, estimated page swipes) rather than stating a verb+resource, so an agent must infer that this is a Screen Time usage report. It also uses unexplained project jargon ("the draft", "where they are now"), which leaves the scope partly opaque. It is distinguishable from siblings like find_apps or optimize_by_usage only by inference.

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 never says when to call this tool rather than a sibling such as find_apps or optimize_by_usage, and offers no exclusions or prerequisites. The device-vs-mac discussion is guidance for choosing a parameter value, not guidance for choosing this tool, so the when-to-use question remains unanswered.

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