Skip to main content
Glama

Save a dashboard

view_save
Idempotent

Keep a view under a name, like the company's weekly dashboard, and replace what it shows whenever you like (same blocks as view_show). view_link makes one-time links to its latest version. Costs $0.01 per call; nothing if it fails.

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": {
      "name": "<name>",
      "title": "<title>",
      "blocks": "<blocks>"
    },
    "name": "view_save"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameYesThe saved view's name, like weekly-sales.
titleYes
blocksYesblocks is a list, drawn top to bottom. Each block is one of: {"type": "heading", "text"}; {"type": "text", "text"} (blank lines make paragraphs); {"type": "metrics", "items": [{"label", "value", "format", "currency", "change" (percent), "better": "up"|"down", "note", "tone": "good"|"warn"|"bad"}]} (up to 8 numbers in a row); {"type": "chart", "title", "kind": "line"|"bar", "labels": [...], "series": [{"name", "values": [...]}], "format", "currency"} (up to 4 series of up to 400 points); {"type": "bars", "title", "label_header", "value_header", "items": [{"label", "value", "detail", "link", "country" (a two-letter code: shows the flag, and the name when label is left out)}], "format", "currency"} (ranked rows with a bar each, up to 50); {"type": "table", "title", "columns": [{"label", "format", "currency"}], "rows": [[...], ...]} (up to 12 columns and 500 rows); {"type": "list", "title", "items": [{"title", "text", "meta", "link"}]} (up to 100); {"type": "divider"}. format is number, percent (49 means 49%), currency (with currency, like "EUR"), seconds (a length of time), milliseconds or text. bars, table, list and metrics take "width": "half" to sit beside the next half block.
subtitleNoA line under the title, like the period it covers.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=false, idempotentHint=true, destructiveHint=false, so the safety profile is covered. The description adds genuinely new behavioral facts: overwrite semantics under the same name and a per-call price of $0.01 with no charge on failure. It omits auth/permission requirements, which is the main remaining gap.

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

Conciseness5/5

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

Three short sentences: what it does, how it relates to view_link, and the cost. The core behavior is front-loaded and every clause carries information an agent needs. No filler or repetition of schema detail.

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 mutation tool with no output schema and a rich nested blocks schema, the description covers cost, overwrite behavior, and where to find block syntax. What is missing is what the agent gets back (e.g. an identifier or link) and any permission prerequisites. Close to complete for the complexity involved.

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 coverage is 75%, so most parameters are already documented, and the description only loosely refers to 'name' and the blocks payload via the view_show pointer. The 'title' and 'subtitle' parameters and the overwrite-by-name keying of 'name' are not explained beyond the schema. This is the expected baseline-3 case where the schema does the heavy lifting.

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 makes clear this is a create-or-replace of a named view ('Keep a view under a name ... replace what it shows whenever you like'), which is a specific verb+resource combination even if 'save' is only implied. It distinguishes itself from view_link (one-time links) and points at view_show for block format, so an agent can place it among siblings. It does not explicitly rule out view_get/view_delete, keeping it just short of a 5.

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 tells the agent when to use this (persisting a reusable, updatable named view) and names view_link as the alternative when one-time sharing is wanted. The 'same blocks as view_show' pointer also routes the agent for content format. No explicit prerequisites or exclusions (e.g. when to use view_delete instead), so not a 5.

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