Skip to main content
Glama

submit_mutation

Destructive

Submit Ads, SP listing or eBay changes. Marketplace writes for a proposed change. Key grants choose review or direct execution. Schemas: describe(kind='operations'). Accepts operation/request or legacy actionType. Returns a mutation id.

Input Schema

NameRequiredDescriptionDefault
paramsNoAction-specific; schema in describe(kind='operations').
requestNoAds: profile_id, ad_product, entities (one canonical Amazon entity) or entity_ids. ads.rules.*: see describe(kind='operations') `rules`. eBay (ebay.ads.mutation / ebay.listings.mutation / ebay.messages.mutation): ebay_account_id, marketplace_id, items [{entityType, entityId, operation, fields}]; a buyer-message reply is one item {entityType: "conversation", entityId: <conversation_id>, operation: "reply", fields: {text}}.
verboseNoBatch: full rows.
entityIdNoAmazon id; 0 when creating.
metadataNoReviewer fields: rationale, rationale_details, contextSnapshot.
operationNoCanonical operation, e.g. ads.campaigns.update.
profileIdNoAds profile ID.
rationaleNo1-2 sentences, max 280 chars shown on the reviewer's card; longer is cut.
actionTypeNoSee describe(kind='operations').
agent_nameNoShort name of this agent or session, shown with the change.
entityTypeNoEntity class.
idempotencyKeyYes
parentEntityIdNoParent id, e.g. campaign_id.
contextSnapshotNoNumbers used. Max 32 KB.
parentEntityTypeNo
rationaleDetailsNoOptional markdown, max 8000, only when there is more to say (evidence, tables).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / request / description
      Previous value: -"Ads: profile_id, ad_product, entities (one canonical Amazon entity) or entity_ids. ads.rules.*: see describe(kind='operations') `rules`."New value: +"Ads: profile_id, ad_product, entities (one canonical Amazon entity) or entity_ids. ads.rules.*: see describe(kind='operations') `rules`. eBay (ebay.ads.mutation / ebay.listings.mutation / ebay.messages.mutation): ebay_account_id, marketplace_id, items [{entityType, entityId, operation, fields}]; a buyer-message reply is one item {entityType: \"conversation\", entityId: <conversation_id>, operation: \"reply\", fields: {text}}."
  2. Changed5 schema fields changed
    • addedInput schema / additionalProperties
      Added value: +false
    • changedInput schema / properties / actionType / description
      Previous value: -"See list_mutation_types."New value: +"See describe(kind='operations')."
    • removedInput schema / properties / businessProfileId
      Removed value: -{
      -  "description": "Business profile ID.",
      -  "type": [
      -    "integer",
      -    "string"
      -  ]
      -}
    • changedInput schema / properties / params / description
      Previous value: -"Action-specific; schema in list_mutation_types."New value: +"Action-specific; schema in describe(kind='operations')."
    • changedInput schema / properties / request / description
      Previous value: -"Ads: profile_id, ad_product, entities (one canonical Amazon entity) or entity_ids. ads.rules.*: see list_mutation_types `rules`."New value: +"Ads: profile_id, ad_product, entities (one canonical Amazon entity) or entity_ids. ads.rules.*: see describe(kind='operations') `rules`."
  3. Changed1 schema field changed
    • addedInput schema / properties / agent_name
      Added value: +{
      +  "description": "Short name of this agent or session, shown with the change.",
      +  "maxLength": 200,
      +  "type": "string"
      +}
  4. First observed

TDQS

A3.5/5.0
Behavior3/5

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

Annotations already flag destructiveHint=true, openWorldHint=true, and idempotentHint=false, so the safety profile is carried structurally. The description adds two things beyond that: the review-versus-direct-execution path chosen by the key's grants, and that it returns a mutation id (valuable since there is no output schema). It leaves notable gaps, though — it never explains what the required idempotencyKey guarantees given idempotentHint=false, nor what happens on partial failure of a batch.

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

Conciseness4/5

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

Five short, front-loaded sentences with no filler; the core action and the two calling modes come first. A few fragments ('Schemas: describe(kind='operations').') are terse to the point of being cryptic, and 'Marketplace writes for a proposed change' partially repeats the first sentence.

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?

For a 16-parameter, nested, destructive mutation tool, the description does credibly cover the calling modes, the schema lookup path, and the return value. It omits idempotency semantics, batch failure behavior, and any authorization prerequisites, which matter given destructiveHint=true and no output schema.

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 high at 88%, so the baseline is 3. The description goes beyond the schema by explaining the otherwise-unlabeled oneOf: 'Accepts operation/request or legacy actionType,' telling the agent there are two mutually exclusive call shapes and that one is legacy. It also points to describe(kind='operations') for operation-specific payloads rather than restating them.

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 opens with a concrete verb and resource set: 'Submit Ads, SP listing or eBay changes' and 'Marketplace writes for a proposed change.' That distinguishes it from read-side siblings like get_mutations and get_events. It stops short of explicitly naming the near-neighbor update_mutation, but the write-submission purpose is unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

'Marketplace writes for a proposed change' and 'Key grants choose review or direct execution' give real context on when this tool is the right entry point. The pointer to 'describe(kind='operations')' steers the agent for schema lookup. However, there is no explicit guidance on when to use update_mutation instead, nor any stated prerequisites (permissions, approvals) before calling.

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