Run one weapon test to capture metrics, screenshots, and part dumps at chosen moments, helping compare fixes against a baseline.
One probe run: rows, and screenshots and parts dumps at the moments.
| Name | Required | Description | Default |
|---|---|---|---|
| at | No | {action: [seconds]} for screenshots and dumps | |
| tune | No | {weapon: {field: value}}: a fix tried without writing it | |
| parts | No | ||
| shots | No | ||
| slomo | No | ||
| actions | No | ||
| staging | No | a folder whose stage.json overrides assets | |
| weapons | Yes |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full behavioral burden, yet it only hints that screenshots and part dumps are produced. It does not disclose side effects, permission needs, cost, or whether state is mutated by running a probe.
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 terse fragment with no waste, but it is under-specified rather than concise. The output hints are not front-loaded into a clear purpose statement.
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?
An 8-parameter execution tool with no annotations, no output schema, and low parameter documentation needs far more than one cryptic sentence. Nothing an agent requires to invoke it correctly is present.
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 38%; parameters like parts, shots, slomo, actions, and weapons have no descriptions. The phrase "screenshots and parts dumps at the moments" loosely gestures at shots/parts/at but adds no syntax or format detail, so it 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?
"One probe run" essentially restates the tool name, and the trailing fragment "rows, and screenshots and parts dumps at the moments" is too cryptic to state what the run actually does. It does not distinguish this tool from its probe_status/probe_plan siblings.
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 when-to-use guidance, no prerequisites, and no mention of alternatives such as probe_plan or probe_status. An agent has nothing to decide whether to call this versus its siblings.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.