bookmark

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

Annotations declare the safety profile (readOnlyHint=false, destructiveHint=false, idempotentHint=false), so the description doesn't need to re-litigate mutability. It goes beyond them by disclosing the channel-enabled requirement, the printf-style dynamic text behavior, and the TEXT() static_assert constraint, which are real implementation gotchas an agent would otherwise discover by failure.

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?

Three tight sentences, front-loaded with the core action, followed by the channel prerequisite and the formatting constraint. The static_assert sentence is dense but earns its place; nothing is 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?

With only one parameter, no output schema, and annotations covering safety, the description fills the remaining gaps by naming the return shape ({ bookmarked, text, frame, note }) and the channel/formatting constraints. An agent has essentially everything needed to call it correctly.

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 is 3, but the description adds genuine meaning beyond the schema's 'bookmark label in UnrealInsights' by explaining that the text is dynamically formatted yet the Format token must be a TEXT() literal. That nuance is not 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 verb and resource: 'Emit a TRACE_BOOKMARK into the active .utrace at the current frame.' That is precise enough to separate it from the surrounding trace siblings (region_start/region_end, frame_timing) by scope. It stops short of naming an alternative tool, so no explicit sibling 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 prerequisite 'The bookmark channel must be enabled in the trace (default start_trace channels include it)' gives a concrete condition for success. However, it never says when to reach for this tool versus region_start/region_end or other trace markers, so usage is implied rather than directed.

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