viewer_call

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

Annotations already flag destructiveHint=true and openWorldHint=true, so the safety profile is covered. The description still adds real value: the LLSD typed-value encoding for arguments, the instruction to re-read state after writes, and the explicit warning that timeouts must not be blindly retried (a retry/idempotency hazard). These go beyond the 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 tight sentences, front-loaded with the core action and then the two operational caveats. No filler, and the most important constraint (typed values in arguments) comes first.

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 destructive, open-world, no-output-schema tool with 5 undocumented parameters, the description is thin. It never explains what 'expect_reply' or 'timeout' do, how 'api' and 'operation' are discovered/named, or what failures look like, leaving critical invocation details unaddressed.

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% with 5 parameters, so the description must compensate and largely does not. It only illuminates the 'arguments' object via the {$uuid}/{$uri}/{$binary_base64} typed-value convention; 'api', 'operation', 'timeout', and 'expect_reply' remain entirely 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 clear verb+resource: invoking a discovered viewer API operation. It is distinguishable from viewer_api_inspect (discovery) but the description never explicitly names that sibling or the discovery workflow, so sibling differentiation is left to 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 gives post-call advice ('Read state after writes', don't blindly retry timeouts) but no guidance on when to choose this tool over alternatives such as viewer_api_inspect or the many typed sibling tools (ui_click, setting_set, etc.). Usage context is only implied.

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