run_nxt

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

Annotations are completely absent, so the description carries the full burden of behavioral disclosure. The description only says 'run to reduce noise', which is minimal. It does not disclose that this is a heavy computation, requires a view to be open, or what happens to the view (e.g., modifies it in place). No information about side effects, performance, or limitations. Given the absence of annotations, this is insufficient.

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 sentence with no fluff. It is concise and front-loaded with the action. However, given the lack of usage guidelines and behavior details, some additional sentences would be justified, so it could be slightly under-specified, but for what it covers, it is efficient.

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 no annotations, no output schema, and a moderately complex 3-parameter set, the description is incomplete. It fails to explain the interplay between denoise and detail, the expected result (reduced noise), any prerequisites (e.g., view must be open), or how it differs from alternatives. An agent needs more context to invoke it correctly.

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 100%, with each parameter having a description. The description adds only the context that the tool reduces noise, which implies that 'denoise' and 'detail' are noise reduction parameters. However, it does not add new meaning beyond the schema: 'detail preservation' and 'denoise strength' are self-explanatory. Baseline 3 is appropriate because the schema already explains them well.

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 action (Run NoiseXTerminator to reduce noise) and the target (a view). It is specific enough to distinguish from general purpose tools like run_process or run_pjsr, though it doesn't explicitly name siblings. The verb 'run' and resource 'view' are present. Could be improved by mentioning it's specifically for noise reduction, which it already does. Distinguishes from noisy counterparts like run_sxt or run_bxt slightly, but those are similar noise reduction tools.

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 does not specify when to use this tool versus alternatives like run_sxt (which is likely a synonym) or other noise reduction tools. It does not provide context on when noise reduction is appropriate or when to use other processes. No exclusions or alternatives are mentioned. This is a gap: an agent might struggle to decide between run_nxt and run_sxt if both exist.

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