suggest_next_stepRetrieve the single next experiment step from the reasoning engine.
| Name | Required | Description | Default |
|---|---|---|---|
| bean_id | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
| category | Yes | ||
| warnings | Yes | ||
| next_step | Yes |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the description does not need to restate safety. It adds that the result is a 'single' step and comes 'from the reasoning engine,' which is useful, but it does not disclose anything about error behavior or the meaning of 'next.'
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?
The definition is a single, front-loaded sentence with no filler. 'Single' and 'reasoning engine' both earn their place by constraining the result.
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 one-parameter, read-only, idempotent tool with an output schema, the description is close to sufficient. However, it lacks any explanation of what a valid bean_id is, what 'next' means relative to, and when this tool should be selected, leaving some context for the agent to infer.
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 input schema has one required integer parameter, bean_id, with 0% schema description coverage, and the description never mentions bean_id or explains what values are valid. The name is somewhat self-explanatory, but the description adds no semantic meaning beyond the schema.
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 concrete operation ('Retrieve ... next experiment step') and a source ('reasoning engine'), so an agent can tell what the tool returns. It does not explicitly differentiate from sibling tools, but none has an obviously similar name.
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?
No guidance is given about when to call this tool versus alternatives such as diagnose_shot or log_recommendation, and no prerequisites or exclusions are mentioned. The intended use must be inferred from the name and one-line description.
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 sort cleanly into register_*, list_*, set_*, and log_* families with clear resource targets. The main ambiguity is between diagnose_shot and diagnose_preview, which are deliberately similar, and between get_dial_state and suggest_next_step, but the descriptions resolve these reasonably well.
Naming is overwhelmingly consistent snake_case verb_noun, such as register_coffee, list_shots, update_shot, and set_active. Minor exceptions like kb_changelog next to get_kb_version and grinder_math break the pattern slightly.
With 34 tools, the surface is well over the 25+ too-many threshold. The resource families are individually clear, but the assistant would be easier to navigate with fewer, more consolidated tools or less KB introspection surface.
The core dialing workflow is well covered: registration, shot logging, diagnosis, dial state, recipes, and maintenance. However, most registered entities such as grinders, machines, waters, scales, and programs have create+list but no update/delete, and recipes have no unlock/delete lifecycle.