update_beanUpdate coffee bag fields. Changing dial_category changes what the engine advises (G5, C10), so say why in the optional note.
| Name | Required | Description | Default |
|---|---|---|---|
| fields | Yes | ||
| reason | No | Optional free-text note, appended to the bag notes as an ordinary line. Omit it and nothing is written. | |
| bean_id | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
| status | Yes | ||
| message | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already communicate mutability, idempotency, and non-destructiveness. The description adds a genuinely non-obvious side effect: changing dial_category alters what the engine advises (G5, C10), and it recommends explaining the change in the optional note. This goes beyond what annotations and schema alone provide.
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 sentences with no filler. The general update action is front-loaded, and the important dial_category caveat immediately follows. Every sentence earns its place.
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 this many updatable fields, the combination of description, nested schema, annotations, and output schema is sufficient. The only notable gap is lack of explicit alternative routing, which is already reflected in the usage_guidelines score, so it is not double-penalized here.
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% at the top level, but nested fields are individually described in the schema. The description adds meaningful coupling between dial_category and the reason parameter, explaining a consequence not present in the schema. It does not discuss bean_id or the fields wrapper, but those are structurally evident.
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 opens with 'Update coffee bag fields' — a specific verb and resource — and the title reinforces the scope. It does not explicitly name sibling tools to distinguish from, but 'coffee bag fields' clearly separates it from siblings like update_shot and register_coffee.
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 action itself is stated directly, but there is no guidance on when to use this tool versus alternatives such as register_coffee, set_active, or update_shot. The dial_category note is a useful within-tool instruction, not an alternative-routing or when-not-to-use rule.
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.
Each tool maps to a distinct resource or action: register_* and list_* are separated by entity, shot tools are split into log/update/delete/diagnose, and the two diagnose variants are explicitly differentiated by dry-run vs. logged evaluation. There is no meaningful overlap that would make an agent choose the wrong tool if it reads the descriptions.
The vast majority of tools follow a consistent verb_noun snake_case pattern: register_*, list_*, set_*, update_*, log_*, get_*. The only deviations are noun-first compound names like grinder_math and kb_changelog, which are still readable and do not break the overall predictability.
At 34 tools, this server exceeds the 25+ threshold where the interface becomes heavy for an agent to navigate. Many of the tools are simple register_/List_ pairs across seven entity types, which inflates the surface area even though each individual tool is understandable.
Core workflows are well covered: logging, updating, deleting, and diagnosing shots; maintaining equipment; and navigating machine state. However, there are notable lifecycle gaps such as no way to list or delete registered programs, no update/delete operations for most equipment types, and no recipe deletion or unlock, which can leave an agent stuck after certain user requests.