replay_step

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

Annotations already declare readOnlyHint=false, destructiveHint=false, idempotentHint=false and openWorldHint=true, so the mutation profile is covered. The description adds useful behavior beyond that — per-step cursor verification and the paused-autoplay requirement — but says nothing about what happens if verification fails mid-advance, whether partial advances persist, or how errors surface.

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?

One sentence, front-loaded with the action and followed by the two operative constraints. No filler whatsoever.

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?

There is no output schema, so the description is the only place to learn what a successful advance returns or what a verification failure looks like, and it is silent on both. For a stateful replay mutation with an openWorld hint, that is a visible gap.

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 67%: target_id and expected_layout_id are described in the schema, while 'bars' is undocumented except for its 1–10 bounds. The description's 'bounded number of replay bars' only loosely points at that parameter and adds no format or default guidance, so the schema still carries most of the weight.

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 ('Advance ... replay bars') plus a scope qualifier ('bounded number') that separates it from replay_start/replay_stop/replay_autoplay siblings. It never names those siblings explicitly, but the operation is unambiguous.

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?

'autoplay must be paused' is an explicit precondition that tells the agent when this call is legal and implies coordination with the replay_autoplay tool. It stops short of naming alternatives or explaining what to do when the precondition fails.

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