Run isolated main and sub-agent tasks in networkless Docker with explicit text inputs, a host-configured Ollama model, verified artifact delivery, and reviewer oversight.
Run an isolated main/sub-agent team on explicit task and text copies. Requires Docker and a host-configured Ollama model.
| Name | Required | Description | Default |
|---|---|---|---|
| task | Yes | ||
| inputs | No | Explicit text copies keyed by flat filenames; never host paths. | |
| timeout | No |
Changes observed during successful MCP inspections.
v1.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare this is a non-read-only, non-idempotent, non-destructive, closed-world operation, so the safety profile is covered. The description adds the real-world prerequisite context (Docker + host-configured Ollama model) and the 'isolated' execution claim, but never explains side effects, whether runs can be repeated safely, or what a failed prerequisite yields.
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?
Two tight sentences with the action front-loaded and the constraint immediately after; no filler. It is arguably under-specified rather than bloated, 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, three parameters (one a nested map), and an execution tool that mutates state, the description covers the concept and prerequisites but omits what gets produced, failure behavior, and how timeout interacts with long-running agent teams. Adequate but with clear gaps.
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 33%: 'task' and 'timeout' have no schema descriptions, and the 'inputs' description ('flat filenames; never host paths') is already in the schema. The description's phrase 'explicit task and text copies' maps loosely to task/inputs but adds no format, size, or timeout guidance to compensate for the 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?
States a specific verb ('Run') and resource (an isolated main/sub-agent team) acting on a task plus text copies — far more than a restatement of the name. It does not, however, distinguish itself from capsule_demo or capsule_doctor, so an agent has to infer which 'capsule_' variant to pick.
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 prerequisite ('Requires Docker and a host-configured Ollama model') gives useful context for when this call can succeed. There is no guidance on when to choose capsule_run over capsule_demo/capsule_doctor, no exclusions, and no statement of what happens when the prerequisites are absent.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.