Skip to main content
Glama
Sign In

SparkAds

by dev.sparkads
OverviewDiscussionsAdmin

update_creative

DestructiveIdempotent

Edit this advertiser's ad card. Pass only the fields to change; anything omitted keeps its current value. WRITE TOOL, and it costs something: saving resets the card's status to 'pending', so the ad STOPS running until a person approves it again. Say that to the user and get their agreement before calling this. Caps: name 40 characters, tagline 60, one-sentence body 160, url must be https, domain must be a bare hostname like myapp.com. House style: plain words, no exclamation marks, and the sentence says what the product does rather than why it is good.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "update_creative"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlNoWhere the card links to. Must be https.
bodyNoOne sentence saying what the product does.
nameNoThe app name shown on the card.
domainNoBare hostname, e.g. myapp.com. The card takes its logo and colour from here.
taglineNoFour or five words, sits under the name.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.9/5.0
Behavior5/5

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

Annotations only flag destructiveHint=true; the description earns its keep by disclosing the actual consequence — the ad STOPS running until a human re-approves it — which is not derivable from any structured field. It also labels the tool as a WRITE TOOL and mandates surfacing the side effect to the user, well beyond annotation coverage.

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?

Front-loaded with the identity and the highest-stakes fact (status reset), then consent, then caps, then style. Roughly 75 words for a five-parameter mutation tool with no wasted sentences; the cap restatements double as a compact pre-flight checklist.

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?

No output schema exists, but nothing important is missing: the mutation's side effect, the consent requirement, partial-update semantics, field constraints, and editorial style are all covered. For a destructive write tool this is sufficient to call it correctly and safely.

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% with maxLength and https/bare-hostname rules already documented per field, so the repeated caps add only checklist convenience. Genuine added meaning comes from the house style rules (plain words, no exclamation marks, describe what the product does not why it is good), which are content constraints absent from the schema.

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: 'Edit this advertiser's ad card,' and immediately clarifies the patch semantics ('pass only the fields to change'). No sibling tool does anything similar — all five are read-only getters — so the agent can route correctly without opening any 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 the precondition explicitly: the user must be told that saving resets the card to 'pending' and must agree before the call. It also defines partial-update behavior ('anything omitted keeps its current value'), which tells the agent it need not fetch-and-resend full state.

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

All SparkAds toolsInspect
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