Stage Object Highlight

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

With no annotations, the description carries the full burden and does well: it discloses rendering layering ('drawn over everything'), persistence semantics (seconds 0 → until markers_clear), replacement of an existing highlight, and the failure mode ('any name not found' errors). It omits permission/scope requirements and doesn't explain what a 'group' name resolves to, which keeps it from a 5.

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?

Dense and front-loaded — the core action leads, followed by persistence, replacement, and error behavior in a single compact passage. The parenthetical about the page command and single `object` is somewhat cryptic out of context, but no sentence is wasted.

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?

An output schema exists, so the 'Page replies {objects, seconds}' sentence is largely redundant, while genuinely needed context (what `scene` selects, what `color` controls) is missing. A mutation-style visual tool with zero annotations would benefit from stating whether highlights are per-scene and how they persist across scene changes.

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 0%, so the description must compensate for all four parameters. It meaningfully explains `objects` (named object or group) and `seconds` (0 means persist), but never mentions `color` or `scene` at all, leaving half the parameters with no semantic explanation 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 and visual effect ('put a pulsing box outline, drawn over everything') applied to a specific resource ('each named object or group'). The action is unambiguous, but nothing distinguishes it from nearby siblings like stage_object_set or stage_object_drop, so the agent gets no explicit differentiation.

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 implies the use case (visually marking objects) and gives a conditional hint with 'seconds 0 keeps it until markers_clear', but never says when to prefer this over stage_object_set, stage_object_select, or stage_deselect/deselect-style tools. Usage is inferable rather than stated.

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