Step Flow Debug Run

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

Annotations already declare destructiveHint=true and readOnly=false; the description adds the crucial context that 'the steps run for real', i.e. the mutations actually execute, which is exactly the kind of consequence an agent needs. It also explains that 'into' runs in a child context that later calls apply to, clarifying scope behavior, though it does not mention permissions or what happens to the paused run after a non-pausing call.

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?

The core purpose and default are front-loaded before the parenthetical action breakdown, and every clause carries information. It is one densely nested sentence, which makes it slightly harder to parse than a short enumerated list would be.

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 debugger-stepping tool with no output schema, the definition covers the mutation semantics, the child-context scoping of 'into', the breakpoint implications of 'resume' and 'skip_all', and the pause-or-end outcome. That is enough for an agent to call it correctly without guessing at return structure.

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 100%, which sets the baseline at 3, but the description goes further by explaining what each action enum value actually does semantically rather than just restating that 'over' is the default. This adds real meaning beyond the schema for the enum parameter, so it scores above baseline.

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 ('Move a paused debug run and report where it is') and enumerates every action mode, so an agent knows exactly what the tool does. It stops short of naming differentiating siblings like debug_flow_run_to or debug_flow_inspect, so the boundary with those tools is inferred rather than stated.

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 parenthetical for each action supplies selection guidance ('over' as default, 'resume' to the next breakpoint, 'skip_all' to the end ignoring breakpoints), and the required context_id's schema note ties it to debug_flow_start/list_flow_debug_sessions. There is no explicit exclusion telling the agent when to prefer debug_flow_run_to or debug_flow_inspect over this tool.

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