Skip to main content
Glama

Visibility Genies

Save a draft

save_draft
Destructive

Saves an article you wrote in the project's Writing Assistant, where the user reads and edits it: a new draft, with a title and optionally a content template to score it against, or an update of a draft you read with get_saved_drafts. An update passes the draft's updatedAt as you read it and is refused if the draft was saved since, so a person's edits are never written over: read it again and save your changes onto that text. get_saved_drafts lists it as saved by an agent, also after a person edits it. Returns the draft's id, its link in the app, its new updatedAt, and its match with the top pages out of 100 against its template with what to do next, from the Writing Assistant's own measure. Uses no credits and calls no provider. A template from another project is refused.

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": {
      "projectId": "<projectId>",
      "text": "<text>"
    },
    "name": "save_draft"
  }
}

Input Schema

NameRequiredDescriptionDefault
textYesThe whole article, which replaces the draft's text on an update. Plain text, each subheading on its own line starting with '## ' ('### ' one level below), as the Writing Assistant scores it.
titleNoThe draft's title. Needed for a new draft; an update keeps the draft's title when it is omitted.
draftIdNoThe draft to update, from get_saved_drafts. Omit to save a new draft.
projectIdYesRequired. The Visibility Genies project this call works in and is billed to. Call list_projects to find one.
updatedAtNoWith draftId, required: the draft's updatedAt exactly as get_saved_drafts or save_draft last returned it. The update is refused if the draft was saved since, so what a person wrote in the app is never written over.
templateIdNoThe id of one of this project's content templates, from get_saved_content_template, to score the draft against. A new draft without one is not scored; an update keeps the draft's template when it is omitted.

Output Schema

NameRequiredDescriptionDefault
metaNo
draftYes
createdYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.5/5.0
Behavior5/5

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

Annotations only declare readOnlyHint=false, destructiveHint=true and openWorldHint=false; the description goes well beyond by disclosing optimistic concurrency (an update is refused if the draft was saved since, protecting a person's edits), that no credits are used and no provider is called, and that agent saves are still listed as agent-saved after human edits. The destructiveHint is consistent with the stated behavior that text is replaced on update.

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, but the body is one dense run-on paragraph mixing workflow, concurrency, billing, return values and error cases. The return-value sentence duplicates the output schema and the note about get_saved_drafts listing agent saves is tangential, adding bulk without aiding invocation.

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?

For a six-parameter mutation tool with concurrency control, the description covers prerequisites, both modes, refusal conditions, side effects (credits/provider) and cross-project template restriction. Return values are described even though an output schema exists, so nothing an agent needs to call it correctly is missing.

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 100%, so the schema already documents title required-for-new/kept-on-update, templateId scoring behavior on omission, and updatedAt as returned by get_saved_drafts. The description largely restates those conditional rules rather than adding new semantics, so it earns the baseline rather than more.

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?

Opens with a specific verb and resource ('Saves an article you wrote in the project's Writing Assistant') and immediately splits the two modes — new draft vs. update of a draft read via get_saved_drafts — so an agent can distinguish it from siblings like get_saved_drafts or build_content_template without opening a schema.

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?

States exactly when to omit draftId (new draft) versus when to pass draftId plus updatedAt (update), names the sibling to read the draft with, and gives explicit recovery behavior when the write is refused ('read it again and save your changes onto that text'). It also names the exclusion case: a template from another project is refused.

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.

Resources