Evaluate each subject's scenes in a folder of timeline JSON files against an 82-item FPS game feel checklist, returning values, verdicts, a summary, and Markdown reports.
Each subject's scenes judged against the checklist: every measured item's values, rules and verdict, a summary, and a Markdown report written beside them.
| Name | Required | Description | Default |
|---|---|---|---|
| folder | Yes | a folder of <subject>_<scene>_timeline.json files | |
| subject | No |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations at all, the description carries the full behavioral burden. It does disclose one meaningful side effect - a Markdown report is 'written beside' the input files - which is real context beyond the schema. However, it omits whether judging requires an LLM/API cost, permissions, whether outputs overwrite existing reports, and where exactly files land, leaving significant gaps for a write-producing tool.
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?
It is a single, front-loaded sentence with a colon-enumerated output list and no filler. The phrasing is slightly fragmented/grammatically loose, but nothing is wasted and the key action leads.
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?
There is no output schema, so the description must carry the return-value burden - and it does list the judged artifacts and the Markdown report. But for a complex judging tool with no annotations and an undocumented optional parameter, it stops short of the behavioral and routing context an agent would need to invoke it confidently.
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 only 50%: 'folder' is documented in the schema, but the optional 'subject' parameter has no description anywhere. The phrase "Each subject's scenes" hints at the subject concept but never explains that 'subject' is a filter parameter or what format it takes, so the description fails to compensate for the coverage gap.
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 names a real action (judging scenes) and its resource (a folder of subject/scene timelines), and enumerates the outputs: measured values, rules, verdict, summary, and a Markdown report. This is clear enough for an agent to understand intent, but it never distinguishes itself from close siblings like check_timeline or gate_rows, which the agent must pick between.
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?
There is no statement of when to use this tool versus the alternatives (check_timeline, gate_rows, list_scenes). No prerequisites, no input assumptions, no exclusion criteria are given, so the agent must infer placement among siblings on its own.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.