Adjust the remaining weight of a filament spool (e.g. after manual weighing).
| Name | Required | Description | Default |
|---|---|---|---|
| log_print | No | ||
| filament_id | Yes | The filament ID | |
| percent_left | No | ||
| weighed_gross | No | ||
| grams_remaining | No | ||
| empty_spool_weight | No | ||
| log_print_filename | No | ||
| log_print_printer_id | No | ||
| subtract_empty_spool | No | ||
| save_empty_spool_weight | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations are all present and false (readOnlyHint, destructiveHint, etc.), providing a baseline. The description adds a small behavioral context by mentioning 'after manual weighing,' implying it's a write operation to update weight data. It doesn't contradict annotations, and given the annotation coverage, this isn't a major gap. However, it doesn't elaborate on side effects or workflows, so 3 is fair.
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 description is a single, focused sentence with a parenthetical example. Every word adds value, and there is no fluff. It is concise and to the point.
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 10 parameters and no output schema, the description is severely insufficient. It doesn't explain the different ways to specify weight (percent vs grams vs gross), the purpose of logging parameters, or how flags like subtract_empty_spool affect behavior. An agent would be unable to correctly determine required vs optional fields or understand the tool's full capabilities. This is a complex tool that needs much more context.
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 only 10% (only filament_id has a description). The description provides zero information about the other 9 parameters, including the various weight fields (percent_left, weighed_gross, grams_remaining) and flags like subtract_empty_spool. The description completely fails to compensate for the low schema coverage, giving no semantic understanding of what each parameter does or how they interrelate.
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 clearly states the tool's purpose: 'Adjust the remaining weight of a filament spool' with a specific verb and resource. The parenthetical '(e.g. after manual weighing)' adds useful context that differentiates it from sibling tools like assign_filament or get_filament, though it doesn't explicitly name an alternative like the top-tier example.
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 phrase 'after manual weighing' implies a use case but doesn't provide explicit guidance on when to use this tool versus alternatives. It hints at the scenario but gives no 'when not to use' or mentions of sibling tools. This matches 'implied usage' rather than clear direction, so a 3 is appropriate.
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 are clearly separated by resource and action, but several overlapping queue-related tools exist—get_next_queue_item vs get_next_queue_items_for_printers, list_queue vs list_pending_queue_items, and inspect_printer_queue—which could cause misselection. list_custom_fields vs list_custom_fields_for and add_to_queue vs create_print_job add further ambiguity.
Names overwhelmingly follow a verb_noun snake_case pattern with consistent resource nouns like print_job, queue_item, folder, and filament. Minor inconsistencies exist, such as add_to_queue vs create_folder/create_print_job, save_queue_group vs update/create, and the slightly odd home_printer and send_back_for_revision.
With 74 tools, this is far beyond the recommended MCP server size and makes the toolset unwieldy to navigate, even for a broad domain. This clearly falls into the extreme 50+ tool category.
Core operational workflows—queue, print jobs, files, filament, and printer control—are well represented. However, printer lifecycle management is missing (no add/update/delete printer), and maintenance management is limited to a read-only dashboard with no corresponding actions.
