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

Annotations only say readOnlyHint=false, idempotentHint=true, destructiveHint=false; the description adds substantial context beyond that: a failure falls back to the last safe page or Start page, nothing is deleted, and the result confirms selection rather than completed loading. The last point in particular prevents a serious misinterpretation of the response.

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 scoping facts are front-loaded in the first sentence and every later sentence adds a distinct behavioral fact. A couple of clauses ('loads it as its own Show again does') are more verbose than needed but not wasteful.

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 an output schema present, the description need not spell out return values, yet it still clarifies what the result does and does not guarantee. For a 3-parameter, non-destructive display-selection tool the only real gap is the undocumented 'device' parameter.

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 load. It explains view_id ('its newest kept revision unless revision is given') and the role of revision well, but leaves the required 'device' parameter (format, ID style, how it is obtained) completely 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?

Specific verb plus resource ('shows a page the screen keeps again, with its saved answers') identified by view_id, and it states the mutation-like effect that the screen switches to it at once. An agent can distinguish this from read tools such as view_get_state or display_get_current without opening a 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 clearly explains when the call will fail (PAGE_NOT_SHOWABLE: incomplete prior show, expired ttl_seconds, or owner-disabled remote pages), which functions as an implicit when-not guide. It never names a sibling alternative for cases where you want a different page shown, so it stops short of full routing guidance.

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