Retrieve the last run's animation clips with frame data, per-clip eye-clipping metrics, and first-person start, middle, and end images for a weapon facts file.
The last run's clips: frames, the eye's clipping per clip (frames checked, frames with clipping, the most pixels, the deepest seen), and the first-person pictures (start, middle, end).
| Name | Required | Description | Default |
|---|---|---|---|
| facts | Yes | a Gun Kit facts file (gunfacts.json) of the gun |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are supplied, so the description carries the full load. It does disclose the content of the response in useful detail (frames checked, frames with clipping, most pixels, deepest seen, start/middle/end pictures), which is real behavioral context. It omits whether the call is purely read-only, what happens if no run has occurred, and whether the returned pictures are large/expensive.
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?
A single dense sentence that front-loads the resource and then enumerates contents, with no filler. Some of the internal jargon ('the eye's clipping', 'the most pixels, the deepest seen') is terse enough to be slightly ambiguous, but nothing is wasted.
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?
With no output schema, the description usefully supplies the return-field inventory, which is its main value. However, for a tool that depends on a prior run and requires a facts file, it omits preconditions and any failure behavior, leaving an agent to discover the invocation context by trial.
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?
The description never mentions the single 'facts' parameter, but schema description coverage is 100%, so the schema already documents that a gunfacts.json file is required. Baseline 3 applies when the schema does the heavy lifting and the description adds nothing further about the 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 names the specific resource (the last run's clip report) and enumerates what it contains: frames, per-clip clipping stats, and first-person pictures. That is enough for an agent to know this returns diagnostic data about clipping. It stops short of framing the action as a verb or contrasting itself with the sibling hold_report, which appears to be a parallel report tool.
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 guidance on when to call this versus hold_report or run_hands, and no mention of prerequisites (e.g., that a prior run must exist for a 'last run' to be reportable). The phrase 'The last run's' is the only usage signal, and it is implicit.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.