Skip to main content
Glama
newsbubbles

ismail: agent DAW (MCP server)

Stage Gesture Set

stage_gesture_set

Binds a hand shape, hand, and hold time to a VR intent in the gesture map, per person or per scene, and refuses rebinds that would collide with another active intent.

Instructions

Bind a gesture to an intent in the VR gesture map (stage_gestures lists them): shape (a hand shape), hand (left, right, either, both at once), hold_ms (held this long before it acts), off=True switches the intent off. owner="person" (default) is the person's own map and follows them into every scene; owner="scene" is this scene's rows (world.json gestures), which the person's rows win over. A rebind that would make two intents share a shape where both are read is refused, naming the row it collides with. Locked rows (vr_exit, stop, voice_note) never change; fixed rows (travel, frame_shot, select, hold) are wired to how the shape moves. The page takes it live.

Input Schema

NameRequiredDescriptionDefault
offNo
handNo
ownerNoperson
sceneYes
shapeNo
intentYes
scenesNo
hold_msNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.4.0

TDQS

A4.3/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries full burden and does so thoroughly: explains owner modes (person vs scene, person wins), refusal on collisions naming the row, immutable locked rows, fixed rows wired to shape movement, and live page update. This gives rich behavioral context beyond the schema.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single dense paragraph, front-loaded with the main action and then details. Every sentence adds information, but it could be structured more readably with bullet points. No wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 8 parameters, no annotations, and an output schema (so return values needn't be described), the description covers purpose, most parameter meanings, constraints, error cases, and live update. The missing coverage of 'scene' and 'scenes' parameters is the main gap, but overall it is complete enough to call correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate. It explains shape, hand, hold_ms, off, and owner well, but omits any description of the 'scene' parameter (required) and completely ignores the 'scenes' parameter. 'Intent' is only implied. Partial compensation warrants a 3.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource: 'Bind a gesture to an intent in the VR gesture map'. It distinguishes from sibling stage_gestures (which lists) and implicitly from stage_gesture_reset (which resets). An agent can tell exactly what this tool does.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It provides clear context for use, including owner semantics and restrictions on locked/fixed rows. It names stage_gestures for listing but doesn't explicitly state when to use this versus stage_gesture_reset or other alternatives, leaving a small gap.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools