Set Flow Debug Breakpoints

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

Annotations already mark this as a non-readonly, non-destructive, idempotent, open-world mutation, and the description adds real behavior beyond that: invalid steps are refused with the list of valid steps returned, step numbers are the ones Workflow Studio displays, and changes scope to the subflow while the run is inside one. The remove-matching caveat (inner action steps have no breakpoint of their own, so only set or clear removes them) is a subtle failure mode disclosed up front.

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 with the core action and then the four modes, followed by edge cases and the sibling pointer — no filler. It is dense, with the remove/inner-action sentence requiring a second read, but every sentence carries operational information.

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 six-parameter mutation with no output schema, the definition covers the operation semantics, rejection behavior, subflow scoping, and how to verify the resulting breakpoint list via debug_flow_inspect. There is no output schema to explain, and the description does not leave a calling agent guessing.

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 100%, so the baseline is 3, but the description adds meaning the schema cannot: parameters are interpreted as step numbers as shown in Workflow Studio, and remove matches by step number even for steps that cannot themselves hold a breakpoint. It does not elaborate on instance/context_id beyond the schema, but the mode parameters are genuinely enriched.

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 (change a debug run's breakpoints) and immediately enumerates the four modes — set/replace, add, remove, clear — so the agent knows exactly what operation family this is. It is clearly distinct from debug_flow_inspect, which it explicitly designates as the read/list counterpart.

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 mode-selection guidance (replace with set, add or remove some, clear them all) plus an explicit alternative: "To list them, use debug_flow_inspect with view breakpoints." It also flags the subflow case where the operation targets the subflow rather than the root run, which is exactly the kind of conditional an agent would otherwise get wrong.

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