GenFlick

Manage request budget

native.manage_budget

DestructiveIdempotent

Read or change an accepted request's spending allowance, or ask the creator for a precise increase; the budget skill holds the rules. change applies a clear creator instruction with the revisions in budgetStatus (runtime status); read only for an older run or after a revision conflict. propose creates one native question when more authority is needed. use_discretion applies only a previously saved bounded grant and makes no model call. goal changes this accepted request; default changes the native conversation's future defaults; both changes each. Native defaults are available only when budgetStatus or a read returns them. Omit run_id for this request. For older work, use an exact saved run ID returned by a native read. A creator command ID or goalId is not a run ID; do not substitute one or invent a run ID.

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": {
      "work_id": "<work_id>",
      "arguments": "<arguments>",
      "expected_catalog_version": "<expected_catalog_version>",
      "read_skills": "<read_skills>",
      "request_key": "<request_key>"
    },
    "name": "native.manage_budget"
  }
}

Input Schema

Name	Required	Description
`work_id`	Yes
`arguments`	Yes
`read_skills`	Yes	Exact required native skills and their dependencies, copied from the accepted session bootstrap's skills array. Include only entries in that array. General mcp.* guides and native.{studio}.instructions are guidance, not native skill proofs.
`request_key`	Yes
`publication_proposal_id`	No	For native Social scheduling, the exact server-approved publication proposal. This identifier cannot confer approval by itself.
`expected_catalog_version`	Yes	For a new session, read a studios/{studio}/native/{pack} child toolset and copy invocation.catalog_version from a native tool descriptor. Do not use the top-level library version. For calls in an existing session, use that session proposal's catalog_version.

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 5, 2026

TDQS

A3.5/5.0

Behavior3/5

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

Annotations already declare destructive=true, idempotent=true and openWorld=true, so the safety burden is partly carried for it. The description adds genuine context beyond them: revision-conflict detection via expected_revision/expected_settings_revision, the fact that use_discretion makes no model call, the fact that propose surfaces a question to the creator, and the constraint that defaults exist only if budgetStatus or a read returned them. It still does not say what a change actually destroys or how spending behaves at the ceiling, so it is informative rather than complete.

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

Conciseness3/5

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

Purpose is front-loaded in the first clause, but the body is a semicolon-chained block with fragments like 'both changes each.' and 'Native defaults are available only when budgetStatus or a read returns them.' that require re-reading. Most sentences carry real information, so this is density rather than padding, but the lack of structure around five operations hurts scanability.

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?

An output schema exists, so return values need not be described, and the description covers operation selection, revision conflicts, and run_id scoping adequately. For a destructive, open-world, nested-schema tool it still leaves the propose/decline parameter set and the discretion_ceiling semantics unstated, and it leans on an external 'budget skill' the agent must separately load.

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 50%, so the description needs to compensate, and it partially does by pinning down run_id ('omit for this request', never invent one, a goalId is not a run ID) and by restating that scope applies to this request, future defaults, or both. That scope restatement largely duplicates the enum description in the schema. Several parameters - alternative, remaining_work, estimate_evidence, discretion_ceiling, reason - remain undocumented in both schema and description.

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 opening clause names a concrete verb set and resource: read or change an accepted request's spending allowance, or propose a precise increase, with the operation names (change, read, propose, use_discretion) mapped to distinct intents. It does not, however, differentiate itself from close siblings such as raise_work_budget or prepare_work_budget, and terms like 'the budget skill holds the rules' and 'native question' are left undefined.

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 gives per-operation routing conditions: read is only for an older run or after a revision conflict, propose is for when more authority is needed, use_discretion applies only an already-saved bounded grant, and goal vs default vs both is spelled out. It also warns explicitly against substituting a creator command ID or goalId for a run ID, which is a real when-not rule. The gap is that it never routes to an alternative tool, only to alternative operations.

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

All GenFlick tools Inspect

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

Need Help?