Save a replay

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

Annotations declare readOnlyHint=false and destructiveHint=false, and the description adds useful context beyond them: the capture scope (keys, pointer, param changes), the output directory, and that a `warnings` field flags anything a replay cannot reproduce (e.g. slow motion). It stops short of describing return format or file naming specifics.

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 sentences, front-loaded with what gets captured and where it is saved, followed by workflow guidance. Efficient and free of filler, though slightly dense.

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 no output schema, the description usefully explains the returned file and the `warnings` field, and directs the agent to run_scenarios for the next step. Covers what an agent needs to invoke and use the tool, missing only minor details like file naming.

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?

Only one parameter with 100% schema description coverage, so the schema already documents `toTick` and its default. The description restates the default ('default: now') without adding syntax or boundary semantics beyond what the schema provides, so the baseline of 3 applies.

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 (capture everything played since load and save it as a replayable scenario) and a concrete output location (.debuff/replays/). The name 'game_replay' is slightly ambiguous (could imply playback), but the description resolves this by clarifying it saves a scenario, and it implicitly distinguishes itself from run_scenarios, which executes them.

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 a clear when-to-use workflow: 'Use a note's tick to reproduce what the human saw when they flagged it, then run_scenarios with the returned file.' This names the alternative (run_scenarios) and the hand-off, though it does not state explicit exclusions or when NOT to use it.

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