check_view

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

No annotations are provided, so the description carries the full burden. It does add real behavioral value by describing the nature of the result (a difference judgment where small = still there, large = worth looking at) and warns about a false-positive source (a person walking through the shot). However, it never states the concrete return form (boolean, numeric diff, image) or any permission/rate considerations, which is a notable gap given the absence of an output schema.

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?

The core comparison is front-loaded in the first sentence, which is good. The second sentence is long and somewhat discursive, running the motivating question, the scene-change caveat, and an interpretation heuristic together; the interpretation guidance earns its place but could be tightened.

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 tool with no annotations, no output schema, and an entirely undocumented parameter, the description does partially compensate by explaining how to read the comparison qualitatively. But it leaves the concrete output shape, the meaning of `label`, and any failure modes unspecified, so an agent still lacks what it needs to invoke and consume the result confidently.

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% for the single required `label` parameter, so the description must compensate and largely does not. It refers to 'one stored by mark_view', which only weakly hints that `label` identifies a saved view and must match a prior `mark_view` call; the label's format and constraints remain undocumented anywhere.

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 (compare) and resources (the current picture vs. one stored by `mark_view`), and explicitly names the sibling tool responsible for the stored state. An agent can immediately distinguish this from `mark_view` and the other camera-control siblings without opening any 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?

It conveys the operating context clearly: use it to answer whether the camera is still pointed at what it was, and it implies a prerequisite (a view previously stored via `mark_view`). It offers no explicit when-not or alternative tools, but the trigger condition is unambiguous.

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