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

Annotations already declare destructiveHint=true, idempotentHint=true and readOnlyHint=false; the description adds real value by explaining what makes it destructive-prone — `null` clears the filter and `[]` clears the sort — and by confirming partial-update semantics. It does not explain why the tool is flagged destructive overall (e.g. whether unmentioned settings can be reset, or permission requirements), which would be needed to fully justify the flag.

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?

A single front-loaded sentence pairs the core action with a field-by-field list, and the trailing clarifications on partial updates and view-id sourcing are both load-bearing. It is dense but nearly every clause carries a distinct constraint; the parenthetical view-type lists make it slightly hard to scan.

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 11 parameters, a rich annotation set and an output schema present, the description supplies exactly the missing pieces: per-parameter view-type applicability, clearing semantics, and where to obtain `viewId`. Return values need not be described because an output schema exists.

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 73%, and the description goes beyond it by attaching view-type applicability to parameters (`hiddenFields`/`shownFields` only for TABLE/KANBAN/CARD, `dateField` for CALENDAR/GANTT_CHART/TIME_LINE, `resourceField` for TIME_LINE) and by pointing `filter` at the `sheet.read` filter form. The only unexplained parameter is `sheetId`, which lacks a description in the schema as well.

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 and resource ("Change an existing view's settings") and immediately enumerates the mutable fields, so the agent knows exactly what surface the tool touches. It implicitly contrasts with view.create/view.delete through "existing view" and partial-update semantics, though it never names those siblings.

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?

"Only what you pass changes; the view's other settings stay" clarifies the update-vs-replace choice, and "The view id comes from `sheet.schema`" gives the prerequisite lookup path an agent needs before calling. It stops short of explicit exclusions (e.g. when to use view.create instead), so it is clear context without full when/when-not guidance.

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