Skip to main content
Glama

Growomat

by com.growomat
OverviewDiscussionsAdmin

Create keyword

create_keyword

Add a keyword to an ad group. On a platform without keywords (a chat platform), positive keywords are sent as plain-language context hints — write them as the questions people ask — and negatives are dropped; validate_export says so. Returns the full updated/created object. Scoped to the active Space — see set_active_space to switch, or pass space_id to override for this one call.

Input Schema

NameRequiredDescriptionDefault
bodyYesRequest body matching the KeywordCreate schema. Fields below; see the OpenAPI spec for nested object shapes.
space_idNoOverride the active Space for this one call. Defaults to the active Space set via set_active_space (or GROWOMAT_SPACE_ID on the server). Pass to read/write a different Space without changing the session binding.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / body / properties / _native
      Added value: +{
+  "additionalProperties": true,
+  "description": "Platform-only settings, keyed by platform id (for example {\"openai-ads\": {\"budgetKind\": \"LIFETIME\"}}). Each value is stored and returned as sent. The NativeExtensions schema in the OpenAPI spec lists every key each platform reads and where (campaign, ad group or ad) — a lifetime budget, a bidding type, delivery surfaces, the words and image on a card. On update, send the whole object for a platform: it replaces that platform's settings.",
+  "type": "object"
+}
  2. 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 this is a non-read-only, non-destructive write. The description adds real behavioral context beyond that: platform-dependent mutation semantics where negative keywords are silently dropped, the fact that the full updated/created object is returned, and how the active-Space binding affects where the write lands.

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?

Three sentences, action first, then platform caveat, then return behavior and scoping. Dense but every clause carries information; the middle sentence is slightly compressed in a way that takes a re-read.

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 create tool with annotations covering the safety profile, no output schema, and a fully documented nested body schema, the description covers the remaining agent-relevant unknowns: platform-dependent behavior and Space scoping. Anything further (match type rules, bid semantics) is legitimately deferred to the OpenAPI spec.

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 the baseline would be 3, but the description adds interpretive meaning for `body.text` (on chat platforms write keywords as the questions people ask) and clarifies the positive/negative distinction tied to `isNegative`. The `space_id` explanation largely restates the schema's own description, so it is not a full 5.

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 specific verb and resource ("Add a keyword to an ad group") that maps cleanly against siblings like update_keyword, delete_keyword, and list_keywords. It does not explicitly name a sibling it is not, so it stops short of full differentiation, but the operation 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 Guidelines5/5

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

It gives conditional guidance (on platforms without keywords, positives become plain-language context hints and negatives are dropped), points to validate_export as the authority for that behavior, and explains the Space scoping with set_active_space as the alternative and space_id as the per-call override. That is explicit when/how-to-route guidance rather than implied usage.

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

All Growomat 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