controller_record_step_failure

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

With no annotations, the description must carry the full behavioral weight. It discloses the possible downstream transitions (FAILED_RETRY or ROLLBACK), which is valuable. However, it omits other important traits like idempotency, required permissions, or effect on task state beyond the trigger.

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, front-loaded sentence with no fluff. While it could be more structured, it efficiently conveys the core action and a key side effect.

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 tool with two simple string parameters and no output schema, the description is minimal but covers the essential purpose and a critical behavior trigger. However, it lacks sufficient detail for an agent to fully understand invocation context (e.g., when step failure occurs, how reason is used).

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?

The description provides no explanation of the parameters (reason, task_id) despite 0% schema coverage. An agent has no semantic context for what values are appropriate for 'reason' or how 'task_id' relates to a step.

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 clearly states the tool's purpose: recording a step failure, with the specific side effect of possibly triggering FAILED_RETRY or ROLLBACK. It differentiates from sibling tools like record_failure by being step-specific and mentioning state transitions.

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 description provides no explicit guidance on when to use this tool versus alternatives (e.g., record_failure). It only implies usage for step failure recording, leaving ambiguity about context selection.

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