run_sxt

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

With no annotations provided, the description carries the burden of behavioral disclosure. It clearly states that the operation modifies the view in place and produces a new stars view, which are critical side effects. It does not mention reversibility, additional side effects, or prerequisites beyond the is_linear selection, but the key destructive behavior is transparent.

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?

Two sentences with zero wasted words. The first sentence front-loads the core purpose and side effects, while the second adds the crucial parameter guidance. Structure is optimal for scanning.

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?

The description covers the essential what and how, including the in-place modification and the creation of a stars view. It omits how the resulting stars view is named or retrieved, which an agent might need to know to reference it later. However, the agent can likely infer or discover this through list_open_images, so the gap is minor.

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. The description adds semantic value by explaining that is_linear selects the unscreen mode ('off for linear (pre-stretch) data, on for non-linear (stretched) data'), which goes beyond the schema's simple boolean description. Overlap is not elaborated, but the default is clearly documented in the schema.

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 specific verb (Run) and resource (StarXTerminator), and clearly states the action (separate stars from a view) with explicit outcomes: the view is replaced in place with the starless result and a separate stars view is produced. This distinguishes it from sibling star-processing tools by naming the exact algorithm.

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 clear context for when to use the is_linear parameter (off for linear data, on for non-linear), which guides the caller on correct invocation. However, it does not explicitly contrast run_sxt with alternatives like run_bxt or run_nxt, leaving differentiation to the tool name rather than explicit guidance.

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