nr_get_debug_output

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

No annotations are provided, so the description carries the full burden. It indicates a read operation ('Read debug output'), implying no side effects, but it does not explicitly state that it is non-destructive or safe. More transparency about permissions or effects would be beneficial.

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 two sentences long, front-loading the purpose and providing essential usage guidance without unnecessary words. Every sentence earns its place.

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?

Given that an output schema exists, the description does not need to explain return values. It covers the main functionality, usage context, and key parameter behavior. However, it could mention what happens if no debug output exists or if the catch node hasn't stored data.

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 input schema has 0% description coverage, so the description must add meaning. It explains the key parameter behavior: pass null to list all context keys. This is valuable beyond the schema. However, the flow_id parameter is not elaborated beyond its type.

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 it reads debug output from flow context, specifically when a catch node stores errors/debug data. It also explains the behavior of passing key=null to list all keys. However, it does not explicitly distinguish from the sibling nr_get_flow_context, which could be used for general context reading.

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 explicitly says when to use: when a flow has a catch node storing errors/debug data to flow context. It also provides a usage sequence: trigger with nr_inject first, then read. However, it does not mention when not to use or list alternative tools like nr_get_flow_context for other context reading.

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