ACTION_RETRY

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

With no annotations provided, the description carries the full burden, and it does well: it discloses the control-flow contract (next-back wiring), the failure detection model (xxx_success=false vs. require), and that exhausted attempts still fall through to the next node rather than erroring. It omits what happens if target is missing/invalid and whether exhaustion is signalled anywhere, leaving a small gap.

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?

Purpose is front-loaded, followed by mechanics and then the failure-detection gotcha, with no filler sentences. There is a minor formatting blemish (a doubled '。。') and the interpolation/return-format note is appended a bit abruptly, but overall it is dense and scannable.

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 6-parameter control-flow node with no output schema, the description covers the wiring contract, failure semantics, retry-exhaustion behavior, variable interpolation, and the return shape. An agent can call this correctly and diagnose the most common mistake (missing require) from the description alone.

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 real meaning: it explains the require parameter's purpose in depth (most nodes only set xxx_success=false, so require=file_success is needed to treat it as failure), notes that string parameters support ${var} interpolation, and states results are returned as a variable snapshot JSON. That is genuine value beyond the schema text.

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?

The description opens with a precise verb+resource pairing ('failure retry: repeatedly execute the target node chain until success or attempts are exhausted') and describes the retry mechanism concretely. It does not name related control-flow siblings such as ACTION_LOOP or ACTION_TRY_CATCH, so the agent must infer the distinction itself, which keeps it below a 5.

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?

It gives clear wiring instructions (the last node of the target chain must point its next back to this node), states that the run proceeds to this node's next on success or exhaustion, and explains the common pitfall that most nodes only set xxx_success=false so a require must be added. It stops short of explicitly comparing against alternative control-flow tools for when-not-to-use guidance.

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