Apply view state

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

Goes well past the annotations by disclosing undo semantics: view + options form exactly one undo step, timescale is its own step, a taskFilter-only call is no undo step, and application switches are persistent and outside undo. It also states that informational fields (baseline, note, favorite) are ignored rather than applied. Annotations already cover idempotency and non-destructiveness, so this added undo/persistence detail is the real contribution.

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 dense paragraph that front-loads the action and scope before the caveats, and every clause (ignored fields, alternatives, undo granularity) carries information. It is long, but justified by the tool's 7 nested sections, so it stays readable rather than padded.

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 complex, deeply nested apply tool with an output schema present, it covers the essentials an agent needs: restorability from the get-answer shape, ignored fields, required minimum section, undo granularity, and where to go for baseline/favourite selection. Nothing critical to correct invocation is missing.

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 100%, so the baseline expectation is a 3; the description still adds cross-parameter meaning the schema cannot convey, namely which answer fields are informational and ignored on write, that timescale carries rillsoft_timescale_apply semantics, and that taskFilter's id lists are absolute. Useful, but much of the per-field meaning still lives in the schema.

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 action pair ('switches the visible view ... and sets its state') plus the concrete scope (grouping, presentation, secondary view, filters, time scale, application switches). It explicitly distinguishes itself from rillsoft_view_state_get ('in the shape of the ... answer'), rillsoft_baseline_select and rillsoft_view_favorite_select, so an agent can place it among the view/state siblings without opening the 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?

Gives the operating pattern directly ('reading it and applying it back restores the state exactly'), the minimum precondition ('At least one section is required'), and routes two adjacent concerns to other tools: rillsoft_baseline_select for baselines and rillsoft_view_favorite_select for favourite views. That is explicit when-to-use plus named alternatives.

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