step_frames

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

Annotations already declare readOnlyHint=false, destructiveHint=false and openWorldHint=true, and the description adds real value on top: the frame-boundary semantics and the caveat that pause-ignoring nodes and external systems are non-deterministic – a meaningful warning given openWorldHint=true. It doesn't state what happens if called while unpaused or what is returned, keeping it at 4.

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 short sentences, front-loaded with the action and its bounds, then the determinism caveat, then the prerequisite. No filler and nothing buried.

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 parameterized mutation with no output schema, it covers action, bounds, post-condition and determinism risk adequately. The remaining gaps – the optional kind default and the sessionId handshake noted in the schema – are small but real.

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 description coverage is only 33%, so the description has to compensate and partly does: it restates the 1–120 bound on frames and explains that kind selects process versus physics frames. It never mentions sessionId or the default behavior when kind is omitted, leaving the highest-risk parameter undocumented in both places.

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 (advance), the resource (a paused live session), the bounds (1 to 120 frames), the axis (process or physics), and the post-condition (pause again). An agent can distinguish this from set_debug_pause and simulate_input without opening a schema.

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 'Requires set_debug_pause first' plus 'paused live session' tells the agent exactly the state it must establish, which implicitly names the sibling that must precede it. It doesn't spell out when not to use it (e.g. against a running, unpaused project), so it stops short of a full 5.

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