run_mgc

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

With no annotations, the description carries the full burden of behavioral disclosure. It usefully explains prerequisites, filter handling, and MARS file defaults, but it does not state what the tool changes in the image, whether it modifies the view in place, or what output/feedback to expect. This is acceptable but incomplete for an unsupervised agent.

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 three sentences and wastes no words. It front-loads the core operation, then states the most decision-relevant constraints in a logical order. It could be slightly more compact, but every sentence adds value and the structure is coherent.

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 moderately complex process with seven parameters and no output schema, the description covers the key contextual needs: prerequisites, filter selection, defaults, and the data source. It omits explicit guidance on when to prefer this over run_gradient_correction or how to interpret the model window, but these are secondary to correct invocation.

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 meaningful context beyond the schema: it explains that filter is mono-only, that omitting it uses R/G/B bands for color images, that mars_files defaults to PixInsight settings, and that certain metadata must be present. This materially helps an agent choose parameter values.

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 names the operation ('Run MultiscaleGradientCorrection') and its data source (MARS reference database), making the tool's core purpose unmistakable. It does not explicitly contrast with sibling tools like run_gradient_correction, but the MARS-specific wording and filter-band handling set it apart enough to avoid gross confusion.

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 concrete preconditions: the image must be plate-solved and linear, and mono images require flux metadata from run_spfc. It also gives explicit filter-selection rules for mono vs. color images, which tells the agent exactly when and how to invoke the tool. It stops short of naming alternative sibling tools or exclusion criteria, but the guidance is strong.

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