Skip to main content
Glama
Cavi Character Animator MCP

Cavi Character Animator MCP

Official
by cavi-ai

session_control

Manage operation leases to claim, renew, release, or resume expired ownership for a specific Character Animator project, validating against the native root.

Instructions

Claim, renew, release, or resume a matching expired lease for one unknown operation.

Resume requires the expired lease ID, same owner, project ID and exact unknown operation ID. It renews ownership after process/root checks and dispatches no native command or chooser action. Claiming a prepared copy requires its private ID and a fresh observation of that exact native root.

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": {
      "action": "<action>"
    },
    "name": "session_control"
  }
}

Input Schema

NameRequiredDescriptionDefault
ownerNo
actionYes
lease_idNo
ttl_secondsNo
expected_projectNo
prepared_copy_idNo
pending_operation_idNo

Output Schema

NameRequiredDescriptionDefault
ownerYes
stateYes
lease_idNo
expires_atYes
owned_rootNo
project_idYes
prepared_copy_idNo
pending_operationYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

B3.4/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=false, openWorldHint=false, and destructiveHint=false, and the description is consistent with a lease-state mutation. It adds genuine value by stating that resume renews ownership only after process/root checks and dispatches no native command or chooser action, which rules out side effects an agent might otherwise fear. It still does not say what a release invalidates, what a claim does to an existing holder, or what happens when the checks fail.

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?

Four sentences, front-loaded with the action list and then the per-action prerequisites, with no filler. The text is dense with domain jargon, which slows comprehension, but every sentence carries information an agent could use.

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?

This is a seven-parameter, five-action lease lifecycle tool, and an output schema exists so return values need not be explained. Even so, the description omits the 'inspect' action entirely and never explains ttl_seconds or lease expiry semantics, and its undefined terminology means an agent cannot fully reason about the lease model from the description alone.

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 carries the full parameter burden. It partially compensates by tying lease_id to the expired lease, owner to the same owner, expected_project to project ID, pending_operation_id to the exact unknown operation ID, and prepared_copy_id to the private prepared copy. But ttl_seconds (default 600, range 30-3600) is never mentioned, and the mappings are implied rather than explicit, leaving real gaps.

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 opens with concrete verbs (claim, renew, release, resume) applied to a specific resource (a matching expired lease for one unknown operation), so the tool's domain is immediately identifiable. It falls short of a 5 because the action enum also contains 'inspect', which the description never mentions, and terms like 'unknown operation', 'prepared copy', and 'native root' are used without definition.

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

Usage Guidelines3/5

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

It gives concrete preconditions for two of the five actions: resume requires the expired lease ID, same owner, project ID and exact unknown operation ID, and claiming a prepared copy requires its private ID plus a fresh observation of that exact native root. However, it offers no guidance on when to choose this tool over operation_control, inspect, or project_open_prepared_copy, and the 'inspect' action has no stated use case at all.

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