log_recommendationLog a recommended dialing change to allow contradiction/oscillation checking (G2).
| Name | Required | Description | Default |
|---|---|---|---|
| lever | Yes | ||
| direction | Yes | ||
| rationale | Yes | ||
| confidence | Yes | ||
| cited_rules | No | ||
| based_on_shot | No |
| Name | Required | Description | Default |
|---|---|---|---|
| status | Yes | ||
| message | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already signal that this is a non-read, non-idempotent, non-destructive write. The description adds that the entry is stored for later contradiction/oscillation checking, which implies the change is not applied immediately. It does not disclose additional side effects or persistence behavior, but the annotation profile lowers the burden.
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?
One sentence, front-loaded with action and object, with a concise purpose clause. There is no filler or redundant restatement of the title.
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?
For a tool with six parameters, four required, no per-parameter descriptions, and no usage guidance, this description is too thin. An agent may infer the basic intent but lacks enough detail to confidently populate fields like cited_rules and based_on_shot or to know how this log entry interacts with the broader system.
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 0%, and the description does little to compensate. It hints at lever and direction through 'dialing change' but leaves rationale, confidence, cited_rules, and based_on_shot entirely unexplained. The schema enums help, but the description should have clarified how these fields relate to the recommendation workflow.
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 specific action ('Log'), a specific object ('recommended dialing change'), and a clear purpose ('allow contradiction/oscillation checking'). This distinguishes it from sibling tools like log_shot, which logs actual shots, and from tools that directly apply settings.
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 phrasing 'recommended dialing change' implies this is for proposed changes rather than actual observations, and the G2 purpose gives context. However, it never explicitly states when to use this tool versus log_shot or other dialing-related siblings, and it provides no exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Most tools target a clearly distinct resource and action, and the list/register/update/set tool families are easy to tell apart. The closest pair is diagnose_preview and diagnose_shot, which are well-described but similar enough in name that an agent could select the wrong one.
The overwhelming majority of tools follow a consistent verb_noun pattern (list_beans, register_grinder, update_shot, set_active). Minor exceptions like grinder_math and kb_changelog lack the imperative verb prefix, but they are readable and do not create real confusion.
34 tools is above the 25+ threshold and feels heavy even though the domain is fairly rich. The many parallel list_* and register_* tools for beans, grinders, machines, scales, waters, programs, and recipes could plausibly be consolidated or trimmed without losing core capability.
The core shot lifecycle is well covered: log, update, delete, diagnose, and list shots, plus bean registration and maintenance tracking. However, most registered entities lack update/delete tools, and get_rule has no corresponding list_rules tool, leaving some obvious workflow gaps that agents must work around.