retry_saga_step

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

The description reveals that the operation is a state transition subject to governance checks, which is a meaningful behavioral trait for a mutation tool. However, it does not disclose failure modes, side effects, idempotency, or what happens if governance checks fail. With no annotations, the burden is higher, and this short phrase is only partially sufficient.

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 description is a single 13-word sentence with no filler. It front-loads the core action and condition, though it sacrifices helpful detail for brevity.

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 mutation tool with no annotations, no output schema, and three undocumented parameters, this description leaves too many gaps: parameter meanings, return value, error conditions, and the precise role of governance checks. It is enough to understand the basic intent but not to invoke the tool with confidence.

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 0% and the description provides no explanation for saga_id, node_id, or force. The 'force' boolean is especially mysterious—it could bypass governance checks or force scheduling, but the text does not say. The agent cannot infer parameter semantics from this definition.

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 names the action ('Return ... to scheduling'), the target ('failed/rejected/blocked workflow node'), and the condition ('after current governance checks'). It clearly separates the tool from execute_saga_step and trigger_rollback by focusing on retrying blocked/failed nodes. It does not explicitly contrast it with approve_saga_step, but the core purpose 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?

It implies use for nodes in failed/rejected/blocked states that should be re-scheduled after governance checks. It does not specify alternatives or exclusion criteria, such as when to use run_ready_steps or execute_saga_step instead. The absence of explicit when-not guidance keeps this at the implied-usage level.

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