Adds or replaces a pistol or rifle hold so the next run_hands call applies the updated grip preset.
Adds or replaces one authored hold. The next run_hands uses it.
| Name | Required | Description | Default |
|---|---|---|---|
| hold | Yes | side:mark or side:mark:kind | |
| family | Yes | pistol or rifle | |
| preset | Yes | the hold: source, contact (palm_skin or pinch), palm_into and fingers_toward (weights on forward, up, left), offset_cm, push_out, fingers {digit: {rule, target_deg, other_hand}} |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must carry the behavioral burden. It usefully discloses overwrite semantics ('adds or replaces') and a downstream coupling to run_hands, but omits permission/validation behavior, error conditions for bad family or hold strings, and whether changes are reversible or persisted across sessions.
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 short sentences, zero filler, with the mutation semantics front-loaded and the runtime consequence second. Nothing could be cut without losing information.
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 write tool with no annotations, no output schema, and a nested object parameter, the description covers the essential write-and-apply model but leaves out validation behavior, success/failure signaling, and error handling. Adequate for correct invocation but not complete for a mutation.
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 100%, so the baseline is 3: the schema already explains hold format, family enumeration, and the nested preset object. The description adds no parameter-level meaning beyond noting the preset is consumed by the next run_hands.
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 pair and resource: 'Adds or replaces one authored hold,' with the scope narrowed to a single hold. It is distinguishable from list_presets/show_preset by its write semantics, but it never names a sibling and shifts terminology between 'preset' (tool name, param) and 'hold' (description), leaving mild ambiguity.
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 next run_hands uses it' implies the usage context: set this before executing run_hands. However, it gives no explicit when-to-use/when-not guidance, no requirement to inspect with show_preset first, and no note that this mutates stored state versus the read-only siblings.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.