scan_frames

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

Beyond the annotations (readOnlyHint=true, destructiveHint=false, openWorldHint=false), the description discloses a significant side effect: 'The scanned root becomes write-protected.' It also reveals caching behavior and the fact that PixInsight is not invoked. These are exactly the kind of behavioral details that annotations do not provide, and no contradiction exists.

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?

Three tightly packed sentences deliver the purpose, key processing logic, caching, and side effect with zero filler. The most important information is front-loaded, and every clause adds value.

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 the complexity of the tool (folder traversal, classification, caching, write-protection) and the absence of an output schema, the description covers the critical behaviors well. It explains what is reported, how results are cached, and that the root becomes write-protected. However, it does not describe how to retrieve the cached result or what the output structure looks like, leaving a small completeness gap.

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 67%: root and include_frames have descriptions, while recursive does not. The description adds context about the scanning/classification process but does not clarify the recursive parameter or explicitly map include_frames to the reported output. It gives general meaning to the inventory operation but fails to fully compensate for the undocumented recursive parameter.

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 uses the specific verb 'inventory' with a clearly defined resource ('folder tree of FITS files'), then enumerates the exact processing steps (header parsing, classification, grouping, reporting). It explicitly distinguishes itself from PixInsight-based workflows and from sibling tools like fits_header by noting it operates on an entire folder tree and caches results for match_calibration. This leaves no ambiguity about what the tool does.

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 by stating 'Result is cached in the session for match_calibration', which tells an agent to run this before using match_calibration. The 'WITHOUT PixInsight' phrase also hints that it is an alternative to PI-based processing. However, it does not explicitly name sibling alternatives or specify when not to use this tool (e.g., for single-file inspection use fits_header).

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