Skip to main content
Glama
Sign In

Valmera — AI Video Editor

by io.valmera
OverviewDiscussionsAdmin

Select object

select_object

Segments and tracks an object within a window of at most six seconds, seeded by a box or points at a program timestamp. Stores an object definition for placement and occlusion.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "t": "<t>",
      "project_id": "<project_id>"
    },
    "name": "select_object"
  }
}

Input Schema

NameRequiredDescriptionDefault
tYes
idNo
boxNo
endNo
depthNo
labelNo
startNo
pointsNo
project_idYesExplicit project identifier for this request. The connection's navigation pointer does not select the target.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / project_id / description
      Previous value: -"Required immutable scope for this call. Copy the id from list_projects/open_project/project_state; the active-project pointer is never used to guess."New value: +"Explicit project identifier for this request. The connection's navigation pointer does not select the target."
  2. Added

TDQS

B3/5.0
Behavior3/5

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

Annotations already declare this is a non-read-only, non-idempotent, non-destructive, closed-world operation. The description adds genuine context beyond that: the six-second maximum window and the fact that a persistent object definition is stored for placement and occlusion. It does not say what happens at the window boundary, what a repeat call with the same inputs does (relevant since idempotentHint is false), or what is returned.

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?

Two tight sentences with no filler, and the primary action plus its scope are front-loaded. The second sentence is slightly ambiguous in phrasing but not wasteful.

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

Completeness3/5

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

With no output schema and near-zero schema coverage on a nine-parameter mutation tool, the description should carry more of the load: parameter meaning, the depth/layering options, and the result of the call. It covers the core concept adequately but leaves the agent guessing at invocation details.

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

Parameters2/5

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

Schema description coverage is only 11% — eight of nine parameters (t, id, box, points, start, end, label, depth) are undocumented. The description names box/points and implies t and the start/end window, but says nothing about the depth enum (auto/front/behind), what id selects or how label is used, so it leaves most parameters semantically opaque.

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

Purpose4/5

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

The description uses specific verbs (segments, tracks) and a concrete resource (an object), plus the seeding mechanism (box or points) and the time bound (at most six seconds). That is enough to distinguish it from nearby tools like track_point or recolour_object, though the second sentence about storing an object definition muddies whether this is analysis or a persistent write.

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

Usage Guidelines2/5

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

There is no guidance on when to choose this over the many sibling creation/tracking tools (track_point, recolour_object, pin_to_plane, add_subject_effect). The 'six seconds' limit hints at a scope constraint but the agent is never told what to do for longer material or what precondition must hold (e.g. an open project, existing media).

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

All Valmera — AI Video Editor toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources