Skip to main content
Glama

save_proposal

Save a proposal document for user review before implementing a complex project. The proposal MUST include a Models section listing the friendly names of the planned image/still and video models, a "💰 Estimated Cost" section with one estimated USD total and a spending ceiling for the planned project, and a concrete numbered scene/shot or beat list. Default project models are Nano Banana 2.1 (google-nano-banana-2-1) for character/location/shot still images and Gemini Omni 1.2 Flash (google-gemini-omni-1-2) for videos after still-image approval. Keep those raw IDs in tool arguments and use friendly model names in user-facing proposal text. Do not use source-file references such as "from script.md" or vague language such as "approximately X shots" instead of enumerating the planned work. Save the complete proposal but show only a short summary in chat, including models, cost and approval scope. Provide a View full proposal link using the returned reviewUrl and ask for approval or changes in chat. Use native question controls only when the host provides an approval-capable tool. Never require clicking approval in Sequencer or fabricate buttons. Open the link only when the user requests it.

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": {
      "workspaceId": "<workspaceId>",
      "editId": "<editId>",
      "proposalMarkdown": "<proposalMarkdown>"
    },
    "name": "save_proposal"
  }
}

Input Schema

NameRequiredDescriptionDefault
editIdYesThe edit ID to save the proposal to
threadIdNoOptional chat thread ID
sourceMediaNoUploaded media from the original Spark request that must remain available after proposal approval
workspaceIdYesThe workspace ID
productionPlanNoExact production jobs, starting-image media IDs, settings and per-job cost limits. Required for combined plan/image/budget approval.
proposalSummaryNoShort user-facing summary, about 100 to 150 words: concept, runtime/format, shot count, visual/audio direction, friendly models, cost, uncertainty and approval scope. Full script and shot details belong in proposalMarkdown.
proposalMarkdownYesThe full proposal content in Markdown format, including concrete numbered scenes/shots or beats. If based on a script or beat sheet, extract and enumerate the planned shots; do not merely reference the file.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / productionPlan
      Added value: +{
      +  "additionalProperties": false,
      +  "description": "Exact production jobs, starting-image media IDs, settings and per-job cost limits. Required for combined plan/image/budget approval.",
      +  "properties": {
      +    "budgetUsd": {
      +      "maximum": 10000,
      +      "minimum": 0,
      +      "type": "number"
      +    },
      +    "creativeScope": {
      +      "maxLength": 4000,
      +      "minLength": 1,
      +      "type": "string"
      +    },
      +    "jobs": {
      +      "items": {
      +        "additionalProperties": false,
      +        "properties": {
      +          "aspectRatio": {
      +            "type": "string"
      +          },
      +          "duration": {
      +            "exclusiveMinimum": 0,
      +            "maximum": 600,
      +            "type": "number"
      +          },
      +          "jobId": {
      +            "pattern": "^[A-Za-z0-9_-]{1,200}$",
      +            "type": "string"
      +          },
      +          "kind": {
      +            "enum": [
      +              "video",
      +              "audio"
      +            ],
      +            "type": "string"
      +          },
      +          "maxCostUsd": {
      +            "maximum": 10000,
      +            "minimum": 0,
      +            "type": "number"
      +          },
      +          "model": {
      +            "minLength": 1,
      +            "type": "string"
      +          },
      +          "modelSettings": {
      +            "additionalProperties": {
      +              "type": [
      +                "string",
      +                "number",
      +                "boolean"
      +              ]
      +            },
      +            "type": "object"
      +          },
      +          "prompt": {
      +            "maxLength": 12000,
      +            "minLength": 1,
      +            "type": "string"
      +          },
      +          "resolution": {
      +            "type": "string"
      +          },
      +          "sourceMediaId": {
      +            "$ref": "#/properties/productionPlan/properties/jobs/items/properties/jobId"
      +          },
      +          "stylePrompt": {
      +            "type": "string"
      +          },
      +          "voiceId": {
      +            "type": "string"
      +          }
      +        },
      +        "required": [
      +          "jobId",
      +          "kind",
      +          "model",
      +          "prompt",
      +          "duration",
      +          "maxCostUsd"
      +        ],
      +        "type": "object"
      +      },
      +      "maxItems": 40,
      +      "minItems": 1,
      +      "type": "array"
      +    }
      +  },
      +  "required": [
      +    "creativeScope",
      +    "budgetUsd",
      +    "jobs"
      +  ],
      +  "type": "object"
      +}
  2. Changed1 schema field changed
    • addedInput schema / properties / proposalSummary
      Added value: +{
      +  "description": "Short user-facing summary, about 100 to 150 words: concept, runtime/format, shot count, visual/audio direction, friendly models, cost, uncertainty and approval scope. Full script and shot details belong in proposalMarkdown.",
      +  "maxLength": 1800,
      +  "minLength": 1,
      +  "type": "string"
      +}
  3. First observed

TDQS

A3.9/5.0
Behavior4/5

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

With no annotations supplied, the description carries the full burden and does substantial work: it discloses that the call returns a reviewUrl, that the full proposal is saved while only a summary is surfaced, and explicitly forbids fabricating approval buttons or auto-opening links. It does not say whether saving overwrites an existing proposal, what happens on re-save, or what permissions are required.

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?

The purpose is front-loaded and the content requirements are specific, but the description is long and mixes three concerns: invocation requirements, post-call chat UX, and anti-pattern warnings. Some of the chat-display and link-opening instructions repeat constraints already implied by the proposalSummary parameter and could be trimmed.

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?

For a 7-parameter tool with nested productionPlan and sourceMedia objects and no output schema, the description covers what must be produced, what is returned (reviewUrl), and how to present results. The remaining gap is lifecycle behavior: whether this creates or replaces a proposal and how it relates to update_proposal and set_proposal_status.

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 100%, so baseline is 3, but the description adds real meaning beyond the schema: proposalMarkdown must enumerate concrete numbered shots with friendly model names rather than file references, proposal-level cost must be a single USD total plus a ceiling, and raw model IDs belong in tool arguments while friendly names go in user-facing text. It does not clarify the relationship between proposalSummary and proposalMarkdown beyond length expectations, which the schema already covers.

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?

States a concrete verb and resource: save a proposal document for user review before implementing a complex project, and specifies the required contents (Models section, cost ceiling, numbered shot list). It never names or contrasts with siblings such as update_proposal or save_experience_game_proposal, so an agent must infer the boundary from the description alone.

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?

Gives clear timing guidance ('before implementing a complex project') and procedural guidance for the post-save flow: show a short summary in chat, surface the reviewUrl link, ask for approval or changes, use native question controls only when an approval-capable tool exists. It does not say when to use this instead of update_proposal or other save_* variants.

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.