get_engine_stats

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

Annotations already declare the safe read-only/idempotent profile, so the bar is lower. The description adds real value beyond that by specifying these are *live* profiling stats and by fully enumerating the returned fields (including is_editor and engine_version), which is the only place output content is documented since there is no output schema.

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?

Front-loaded single sentence stating purpose, followed by a compact return-field list. The list is long but justified because no output schema exists. Structurally clean with no filler prose.

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 zero-parameter read tool this is nearly complete: purpose plus full return contract. Minor gaps remain — memory units are only implied by field names, and it is unclear whether stats reflect the editor or a running PIE session apart from the is_editor flag.

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?

The tool takes no parameters, so per the rubric the baseline is 4. There is no parameter semantics to clarify, and the description wastes no effort pretending otherwise.

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 ('Report live engine profiling stats') and enumerates the exact metrics returned (FPS/MS, process memory, UObject count, engine version). It does not, however, distinguish itself from close siblings such as get_fps_info, get_memory_usage, or get_engine_info, which cover overlapping ground.

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?

There is no guidance on when to call this rather than get_fps_info, get_memory_usage, get_engine_info, or frame_timing — all of which appear in the sibling list. No preconditions, no timing advice (e.g. only meaningful during PIE).

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