Skip to main content
Glama

Add zoom

add_zoom

PROJECT-SCOPED: this call acts only on the explicit project_id and returns the project identity with its result. Zoom on a time range of the FINAL edited video (output seconds) only when a named event needs the camera to move: a reveal, a UI target, a punchline, an explicit user beat. A talking-head already in frame does NOT need a punch-in. strength 0.05-4.5 (default 0.15; above 1.0 is a dramatic 2x+ punch). mode: 'ease' (default, smooth ramp — use this), 'push_in' / 'pull_out' (continuous Ken Burns drift), 'punch' (instant snap — ONLY the single biggest peak or an explicit punch-in request, never every few seconds). TWO ways to aim, and they answer different requests: rect=[x0,y0,x1,y1] (fractions of the output frame, read off look_at's grid) FRAMES A REGION — the tool solves strength and centre so that box fills the frame with margin, THE way to 'zoom into the message / that button / this panel', and its result reports where the region lands on screen. cx/cy instead PIN A POINT: that point keeps its exact screen position while everything magnifies around it — right for emphasis on a subject that is already well-composed, and wrong for framing a thing near an edge (an edge point stays at the edge at any strength — it never slides to centre). Pass rect OR cx/cy, not both; if both arrive the rect wins (it already determines the centre) and the call still succeeds. Omitting all targets uses the frame center and returns a quality advisory. Coordinates may come from look_at, the filmstrip, user direction, or the editor's own judgment; no prior evidence call is required. Zero zooms is often correct. Do not sprinkle punches on 'important sentences'. punch_in_on_emphasis is only for an explicit punch-in-on-stressed-words request. If the zoom should MOVE while pushed in — 'then move it to X', 'keep it and go to the next message', 'follow the cursor' — that is ONE add_zoom_path (its keyframes take rect too), never a chain of static zooms.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
cxNo
cyNo
endYes
modeNo
rectNo
startYes
purposeNoThe nameable narrative or visible reason for this zoom.
strengthNo
project_idYesRequired immutable scope for this call. Copy the id from list_projects/open_project/project_state; the active-project pointer is never used to guess.
motion_motifNoActive Blueprint motion motif id this event executes; never 'hold'.
target_evidence_idsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Annotations only say not read-only and not destructive, so the description carries the burden. It details behavioral nuances: rect vs cx/cy semantics, precedence rules ('if both arrive the rect wins'), default behavior when targets are omitted, and result reporting ('returns the project identity... reports where the region lands on screen'). No contradiction with annotations.

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 long but every sentence adds value. It is front-loaded with the scope constraint and structured logically: when, how (strength/mode), aiming (rect/cx/cy), precedence, fallback, and routing to add_zoom_path. No redundant or fluff sentences; density is appropriate for the tool's complexity.

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

Completeness5/5

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

The description covers all necessary decision points: when to use, how to choose between rect and cx/cy, strength semantics, mode selection, edge cases (edge points), default behavior, and when to defer to add_zoom_path. With no output schema, it even describes the result content. Nothing an agent needs to call this correctly is missing.

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

Parameters4/5

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

Schema coverage is only 27%, so the description must compensate. It thoroughly explains rect, cx/cy, strength (with value ranges and effects), mode (with per-mode behavior), and start/end implicitly. It does not explain motion_motif or target_evidence_ids, but these are peripheral to core usage; the main parameters are richly documented beyond the schema.

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 the exact verb and resource ('Zoom on a time range of the FINAL edited video') and immediately clarifies scope ('PROJECT-SCOPED'). It explicitly distinguishes itself from the sibling add_zoom_path ('that is ONE add_zoom_path, never a chain of static zooms'), so an agent can tell them apart without inspecting schemas.

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

Usage Guidelines5/5

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

Provides explicit when-to-use conditions ('only when a named event needs the camera to move: a reveal, a UI target, a punchline'), negative guidance ('A talking-head already in frame does NOT need a punch-in'), and strong direction on when not to use it ('Zero zooms is often correct'). It names the alternative tool (add_zoom_path) for moving zooms, leaving no ambiguity.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.